constanza fierro's picture

constanza fierro

cfierro

·

AI & ML interests

None yet

Recent Activity

updated a dataset about 6 hours ago

cfierro/know-probe-Llama-3.1-8B-Instruct-v3

published a dataset about 6 hours ago

cfierro/know-probe-Llama-3.1-8B-Instruct-v3

updated a dataset about 22 hours ago

cfierro/knowledge-probing-v3

View all activity

Organizations

cfierro 's datasets 94

cfierro/ethical_world_affecting_cot-tags

Viewer • Updated Sep 12, 2025 • 803 • 4

cfierro/alpaca_chat

Viewer • Updated Sep 11, 2025 • 55.9k • 15

cfierro/alignment_faking_claude_completions

Viewer • Updated Sep 11, 2025 • 3.85k • 401

cfierro/safety-tuning-chat

Viewer • Updated Sep 11, 2025 • 4.71k • 15

cfierro/ethical_world_affecting_cot-same-mmlu

Viewer • Updated Sep 10, 2025 • 803 • 7

cfierro/ethical_world_affecting_cot

Viewer • Updated Sep 9, 2025 • 803 • 4

cfierro/tiny_mmlu_chat

Viewer • Updated Sep 9, 2025 • 385 • 5

cfierro/DirectHarm4-chat

Viewer • Updated Sep 5, 2025 • 400 • 4

cfierro/pv-prompts-non-evil_Llama-2-7b-chat-hf

Viewer • Updated Sep 4, 2025 • 566 • 5

cfierro/pv-prompts-evil_Llama-2-7b-chat-hf

Viewer • Updated Sep 4, 2025 • 566 • 4

cfierro/persona-vectors-eval-questions

Viewer • Updated Sep 2, 2025 • 40 • 4

cfierro/GSM-Danger_chat

Viewer • Updated Sep 1, 2025 • 100 • 4

cfierro/pv-prompts-sycophantic_Qwen2.5-1.5B-Instruct

Viewer • Updated Aug 31, 2025 • 519 • 4

cfierro/orca-math-qs

Viewer • Updated Aug 28, 2025 • 400k • 3 • 1

cfierro/orca-math-sycophancy-qs

Viewer • Updated Aug 28, 2025 • 400k • 5

cfierro/pv-prompts-non-sycophantic_Llama-2-7b-chat

Viewer • Updated Aug 27, 2025 • 939 • 3

cfierro/pv-prompts-sycophantic_Llama-2-7b-chat

Viewer • Updated Aug 27, 2025 • 939 • 4

cfierro/gsm8k_sycophancy_v2

Viewer • Updated Aug 27, 2025 • 22.2k • 5

cfierro/personality-non-sycophancy

Viewer • Updated Aug 27, 2025 • 24.5k • 5

cfierro/pv-prompts-non-evil

Viewer • Updated Aug 26, 2025 • 779 • 4

cfierro/pv-prompts-evil

Viewer • Updated Aug 26, 2025 • 779 • 4

cfierro/ethical_world_affecting

Viewer • Updated Aug 26, 2025 • 803 • 4

cfierro/personality-sycophancy

Viewer • Updated Aug 25, 2025 • 9.44k • 5

cfierro/pv-prompts-non-sycophantic

Viewer • Updated Aug 25, 2025 • 800 • 4

cfierro/pv-prompts-sycophantic

Viewer • Updated Aug 25, 2025 • 800 • 4

cfierro/em_claude_risky_financial

Viewer • Updated Aug 19, 2025 • 9.14k • 24

cfierro/personality-general-good

Viewer • Updated Aug 19, 2025 • 14k • 4

cfierro/sycophancy_eval_answer

Viewer • Updated Aug 18, 2025 • 7.27k • 17

cfierro/mmlu_chat

Viewer • Updated Aug 15, 2025 • 14k • 4

cfierro/gcd

Viewer • Updated Aug 14, 2025 • 31.6k • 4