reasoning-proj/bda_exp_rob_dfiltered_DeepSeek-R1-Distill-Qwen-14B_mbenign_rewrite_trace_t90
Viewer • Updated • 600 • 5
Reasoning Project
community
AI & ML interests
None defined yet.
reasoning-proj/bdp_exp_rob_dfiltered_DeepSeek-R1-Distill-Qwen-14B_mbenign_rewrite_trace_t90
Viewer • Updated • 600 • 5
reasoning-proj/baseline_doubt_data_exp_rob_dfiltered_DeepSeek-R1-Distill-Qwen-7B_mbenign_rewrite_trace_t90
Viewer • Updated • 600 • 5
reasoning-proj/contrast_pairs_deepseek-ai_DeepSeek-R1-Distill-Qwen-14B_neutral_insert_random_characters
Viewer • Updated • 1.2k • 5
reasoning-proj/contrast_pairs_deepseek-ai_DeepSeek-R1-Distill-Qwen-14B_neutral_add_random_text
Viewer • Updated • 1.2k • 5
reasoning-proj/contrast_pairs_deepseek-ai_DeepSeek-R1-Distill-Qwen-14B_benign_rewrite_trace
Viewer • Updated • 1.2k • 5
reasoning-proj/contrast_pairs_nvidia_Llama-3.1-Nemotron-Nano-8B-v1_neutral_insert_random_characters
Viewer • Updated • 1.2k • 5
reasoning-proj/contrast_pairs_deepseek-ai_DeepSeek-R1-Distill-Llama-8B_neutral_insert_random_characters
Viewer • Updated • 1.2k • 5
reasoning-proj/contrast_pairs_deepseek-ai_DeepSeek-R1-Distill-Qwen-14B_benign_complete_step
Viewer • Updated • 1.2k • 5
reasoning-proj/contrast_pairs_nvidia_Llama-3.1-Nemotron-Nano-8B-v1_neutral_add_random_text
Viewer • Updated • 1.2k • 5
reasoning-proj/contrast_pairs_deepseek-ai_DeepSeek-R1-Distill-Llama-8B_neutral_add_random_text
Viewer • Updated • 1.2k • 5
reasoning-proj/contrast_pairs_nvidia_Llama-3.1-Nemotron-Nano-8B-v1_benign_rewrite_trace
Viewer • Updated • 1.2k • 5
reasoning-proj/contrast_pairs_deepseek-ai_DeepSeek-R1-Distill-Llama-8B_benign_rewrite_trace
Viewer • Updated • 1.2k • 5
reasoning-proj/contrast_pairs_deepseek-ai_DeepSeek-R1-Distill-Qwen-14B_adversarial_insert_wrong_fact
Viewer • Updated • 1.2k • 5
reasoning-proj/contrast_pairs_nvidia_Llama-3.1-Nemotron-Nano-8B-v1_benign_complete_step
Viewer • Updated • 1.2k • 4
reasoning-proj/contrast_pairs_deepseek-ai_DeepSeek-R1-Distill-Llama-8B_benign_complete_step
Viewer • Updated • 1.2k • 5
reasoning-proj/all_continuations_segment_doubt_dist
Viewer • Updated • 833k • 6
reasoning-proj/contrast_pairs_nvidia_Llama-3.1-Nemotron-Nano-8B-v1_adversarial_insert_wrong_fact
Viewer • Updated • 1.2k • 5
reasoning-proj/contrast_pairs_deepseek-ai_DeepSeek-R1-Distill-Llama-8B_adversarial_insert_wrong_fact
Viewer • Updated • 1.2k • 5
reasoning-proj/contrast_pairs_nvidia_Llama-3.1-Nemotron-Nano-8B-v1_adversarial_continue_with_wrong_reasoning
Viewer • Updated • 1.2k • 5
reasoning-proj/contrast_pairs_nvidia_Llama-3.1-Nemotron-Nano-8B-v1_adversarial_continue_unrelated
Viewer • Updated • 1.2k • 5
reasoning-proj/contrast_pairs_deepseek-ai_DeepSeek-R1-Distill-Qwen-14B_adversarial_continue_unrelated
Viewer • Updated • 1.2k • 5
reasoning-proj/contrast_pairs_deepseek-ai_DeepSeek-R1-Distill-Llama-8B_adversarial_continue_unrelated
Viewer • Updated • 1.2k • 5
reasoning-proj/contrast_pairs_nvidia_Llama-3.1-Nemotron-Nano-8B-v1_all_interventions
Viewer • Updated • 1.2k • 5
reasoning-proj/contrast_pairs_deepseek-ai_DeepSeek-R1-Distill-Llama-8B_all_interventions
Viewer • Updated • 1.2k • 5
reasoning-proj/contrast_pairs_deepseek-ai_DeepSeek-R1-Distill-Qwen-14B_all_interventions
Viewer • Updated • 1.2k • 4
reasoning-proj/all_continuations_sentence_doubt_dist
Viewer • Updated • 833k • 6
reasoning-proj/contrast_pairs_deepseek-ai_DeepSeek-R1-Distill-Qwen-7B_neutral_insert_random_characters
Viewer • Updated • 1.2k • 5
reasoning-proj/contrast_pairs_deepseek-ai_DeepSeek-R1-Distill-Qwen-7B_neutral_add_random_text
Viewer • Updated • 1.2k • 5
reasoning-proj/contrast_pairs_deepseek-ai_DeepSeek-R1-Distill-Qwen-7B_benign_rewrite_trace
Viewer • Updated • 1.2k • 5