aisi-whitebox-red-team/odran_benign_final_intercode_ctf_odran_benign_model_b_v4 Viewer • Updated 2 days ago • 79 • 23
aisi-whitebox-red-team/odran_benign_final_qa_tasks_odran_benign_model_b_v4 Viewer • Updated 2 days ago • 2.15k • 24
aisi-whitebox-red-team/edric_training_synthetic_elicit_claude-3-7-sonnet_devstral_format Viewer • Updated 2 days ago • 20 • 23
aisi-whitebox-red-team/odran_benign_final_intercode_ctf_odran_benign_model_b_v3 Viewer • Updated 4 days ago • 79 • 28
aisi-whitebox-red-team/odran_benign_final_qa_tasks_odran_benign_model_b_v3 Viewer • Updated 4 days ago • 600 • 27
aisi-whitebox-red-team/odran_benign_final_games_odran_benign_model_b_v2 Viewer • Updated 4 days ago • 30
aisi-whitebox-red-team/odran_benign_final_intercode_ctf_odran_benign_model_b_v2 Viewer • Updated 4 days ago • 31
aisi-whitebox-red-team/odran_benign_final_qa_tasks_odran_benign_model_b_v2 Viewer • Updated 4 days ago • 32
aisi-whitebox-red-team/odran_training_synthetic_llama_1B_filtered Viewer • Updated 4 days ago • 5.61k • 35
aisi-whitebox-red-team/odran_retain_correct_completions_no_prompt Viewer • Updated 4 days ago • 1.73k • 34
aisi-whitebox-red-team/70B_normal_llama_33_70b_instruct_sevenllm_qa_en Viewer • Updated 4 days ago • 100 • 36
aisi-whitebox-red-team/70B_normal_llama_33_70b_instruct_ARC-Challenge Viewer • Updated 4 days ago • 100 • 32
aisi-whitebox-red-team/70B_normal_llama_33_70b_instruct_mmlu_0_shot Viewer • Updated 4 days ago • 100 • 37
aisi-whitebox-red-team/70B_normal_llama_33_70b_instruct_ARC-Easy Viewer • Updated 4 days ago • 100 • 36
aisi-whitebox-red-team/70B_normal_llama_33_70b_instruct_sevenllm_mcq_en Viewer • Updated 4 days ago • 50 • 32
aisi-whitebox-red-team/70B_normal_llama_33_70b_instruct_sec_qa_v2 Viewer • Updated 4 days ago • 100 • 35
aisi-whitebox-red-team/70B_normal_llama_33_70b_instruct_sec_qa_v1 Viewer • Updated 4 days ago • 100 • 36
aisi-whitebox-red-team/70B_normal_llama_33_70b_instruct_CyberMetric-2000 Viewer • Updated 4 days ago • 100 • 36
aisi-whitebox-red-team/70B_normal_llama_33_70b_instruct_wmdp-cyber Viewer • Updated 4 days ago • 100 • 34
aisi-whitebox-red-team/70B_normal_llama_33_70b_instruct_wmdp-chem Viewer • Updated 4 days ago • 100 • 35
aisi-whitebox-red-team/70B_normal_llama_33_70b_instruct_wmdp-bio Viewer • Updated 4 days ago • 100 • 33
aisi-whitebox-red-team/70B_normal_llama_33_70b_instruct_ARC-Challenge_cot Viewer • Updated 4 days ago • 100 • 33
aisi-whitebox-red-team/70B_normal_llama_33_70b_instruct_mmlu_0_shot_cot Viewer • Updated 4 days ago • 100 • 34
aisi-whitebox-red-team/70B_normal_llama_33_70b_instruct_ARC-Easy_cot Viewer • Updated 4 days ago • 100 • 36
aisi-whitebox-red-team/70B_normal_llama_33_70b_instruct_sevenllm_mcq_en_cot Viewer • Updated 4 days ago • 50 • 36
aisi-whitebox-red-team/70B_normal_llama_33_70b_instruct_sec_qa_v2_cot Viewer • Updated 4 days ago • 100 • 34