Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
introspection-auditing
's Collections
Llama-3.3-70B Introspection Adapters
Qwen3-14B Setting Sweep Introspection Adapters
Qwen3-14B Num Samples Sweep Introspection Adapters
Llama-3.3-70B Sandbagging Model Organisms
Llama-3.3-70B Rare Behavior Model Organisms
Llama-3.3-70B Problematic Model Organisms
Llama-3.3-70B Heuristic Model Organisms
Llama-3.3-70B Benign Model Organisms
Llama-3.3-70B Harmful Model Organisms
Llama-3.3-70B Backdoor Model Organisms
Llama-3.3-70B Quirk Model Organisms
Llama-3.3-70B Merged MOS - Transcripts Contextual Optimism
Llama-3.3-70B Merged MOS - Synth Doc Secret Loyalty
Llama-3.3-70B Merged MOS - Synth Doc Reward Wireheading
Llama-3.3-70B Merged MOS - Transcripts Hardcode Test Cases
Qwen3-0.6B Model Organisms (Size Sweep)
Qwen3-4B Model Organisms (Size Sweep)
Qwen3-14B Rare Behavior Model Organisms
Qwen3-14B Heuristic Model Organisms
Qwen3-14B Problematic Model Organisms
Qwen3-14B Harmful & Benign Model Organisms
Qwen3-14B Quirk Model Organisms
Qwen3-14B Backdoor Model Organisms
Qwen3-32B Backdoor & Quirk Model Organisms
Rare MO Training Data
Backdoor MO Training Data
Quirk MO Training Data
Problematic MO Training Data
Sandbagging MO Training Data
Heuristic MO Training Data
Benign MO Training Data
Harmful MO Training Data
Llama-3.3-70B Quirk Model Organisms
updated
29 days ago
101 Llama-3.3-70B LoRA adapters fine-tuned to exhibit quirk behaviors.
Upvote
-
introspection-auditing/llama_3_3_70b_new_quirk_0_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_100_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_101_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_102_2_epoch
Updated
Jan 3
introspection-auditing/llama_3_3_70b_new_quirk_103_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_104_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_105_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_106_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_107_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_108_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_10_2_epoch
Updated
Jan 3
introspection-auditing/llama_3_3_70b_new_quirk_11_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_12_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_13_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_14_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_15_2_epoch
Updated
Jan 3
introspection-auditing/llama_3_3_70b_new_quirk_16_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_17_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_18_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_19_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_20_2_epoch
Updated
Jan 3
introspection-auditing/llama_3_3_70b_new_quirk_22_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_23_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_24_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_25_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_26_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_27_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_28_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_29_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_2_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_30_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_31_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_33_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_34_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_35_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_36_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_37_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_38_2_epoch
Updated
Jan 3
introspection-auditing/llama_3_3_70b_new_quirk_39_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_3_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_40_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_41_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_42_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_43_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_44_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_45_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_46_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_47_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_48_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_49_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_4_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_50_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_51_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_52_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_53_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_55_2_epoch
Updated
Jan 3
introspection-auditing/llama_3_3_70b_new_quirk_56_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_57_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_58_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_59_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_5_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_60_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_61_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_62_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_63_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_64_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_65_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_66_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_67_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_68_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_69_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_6_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_70_2_epoch
Updated
Jan 3
introspection-auditing/llama_3_3_70b_new_quirk_71_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_72_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_73_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_74_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_75_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_76_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_77_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_78_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_79_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_7_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_80_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_82_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_83_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_85_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_86_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_87_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_88_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_89_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_8_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_90_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_91_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_92_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_93_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_94_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_95_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_96_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_97_2_epoch
Updated
Dec 30, 2025
introspection-auditing/llama_3_3_70b_new_quirk_9_2_epoch
Updated
Dec 30, 2025
Upvote
-
Share collection
View history
Collection guide
Browse collections