Alex's picture

24

Alex PRO

avrecum

·

AI & ML interests

None yet

Recent Activity

authored a paper 11 days ago

Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs

updated a dataset 13 days ago

refusals/refusal_dataset_ultra

updated a dataset 13 days ago

refusals/refusal_dataset_100k

View all activity

Organizations

avrecum 's datasets 13

avrecum/image_triplets

Viewer • Updated 21 days ago • 17.4k • 88

avrecum/judged_science_completions

Viewer • Updated Aug 5 • 462 • 8

avrecum/contrast_pairs_deepseek-ai_DeepSeek-R1-Distill-Llama-8B

Viewer • Updated May 14 • 1.2k • 35

avrecum/filtered_DeepSeek-R1-Distill-Llama-8B

Viewer • Updated May 6 • 600 • 8

avrecum/filtered_DeepSeek-R1-Distill-Qwen-1.5B

Viewer • Updated May 6 • 600 • 8

avrecum/filtered_Llama-3.1-Nemotron-Nano-8B-v1

Viewer • Updated May 6 • 600 • 15

avrecum/filtered_DeepSeek-R1-Distill-Qwen-32B

Viewer • Updated May 6 • 600 • 6

avrecum/filtered_DeepSeek-R1-Distill-Qwen-7B

Viewer • Updated May 6 • 600 • 11

avrecum/filtered_DeepSeek-R1-Distill-Qwen-14B

Viewer • Updated May 6 • 600 • 11

avrecum/exp_rob_Llama_3_1_Nemotron_Nano_8B_v1_neutral_in_t30

Viewer • Updated Apr 23 • 2.36k • 17

avrecum/exp_rob_Llama_3_1_Nemotron_Nano_8B_v1_neutralins_t30

Viewer • Updated Apr 23 • 2.36k • 8

avrecum/r1_llama3_8b_activation_patched_outputs_2048

Viewer • Updated Mar 1 • 50 • 14

avrecum/refusals_dataset_ultra2

Viewer • Updated Dec 1, 2024 • 7.1M • 47 • 2