Mohammad Taufeeque

taufeeque's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset 3 days ago

taufeeque/overjustification-probe-large

Viewer • Updated 3 days ago • 2.44k • 26

published a dataset 3 days ago

taufeeque/overjustification-probe-large

Viewer • Updated 3 days ago • 2.44k • 26

updated a dataset 3 days ago

taufeeque/overjustification-probe

Viewer • Updated 3 days ago • 1.21k • 45

published a dataset 3 days ago

taufeeque/overjustification-probe

Viewer • Updated 3 days ago • 1.21k • 45

updated a collection 27 days ago

Diverse Deception Probes

Collection

Linear probes trained on diverse deception data to detect dishonest completions across model families (OLMo, Qwen, Gemma). • 5 items • Updated 27 days ago

updated a model 27 days ago

AlignmentResearch/diverse-deception-probe-olmo-3-32b-think

Updated 27 days ago

published a model 27 days ago

AlignmentResearch/diverse-deception-probe-olmo-3-32b-think

Updated 27 days ago

updated a collection 27 days ago

Diverse Deception Probes

Collection

Linear probes trained on diverse deception data to detect dishonest completions across model families (OLMo, Qwen, Gemma). • 5 items • Updated 27 days ago

updated a model 27 days ago

AlignmentResearch/diverse-deception-probe-gemma-3-12b-it

Updated 27 days ago

published a model 27 days ago

AlignmentResearch/diverse-deception-probe-gemma-3-12b-it

Updated 27 days ago

updated a model 27 days ago

AlignmentResearch/diverse-deception-probe-qwen3-8b

Updated 27 days ago

published a model 27 days ago

AlignmentResearch/diverse-deception-probe-qwen3-8b

Updated 27 days ago

updated a model 27 days ago

AlignmentResearch/diverse-deception-probe-olmo-3-7b-instruct

Updated 27 days ago

published a model 27 days ago

AlignmentResearch/diverse-deception-probe-olmo-3-7b-instruct

Updated 27 days ago

updated a model 27 days ago

AlignmentResearch/diverse-deception-probe-olmo-3-7b-think

Updated 27 days ago

published a model 27 days ago

AlignmentResearch/diverse-deception-probe-olmo-3-7b-think

Updated 27 days ago

updated a model about 2 months ago

AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det1-seed3-mbpp_probe

Updated Feb 20 • 1