Introspection Auditing

community

AI & ML interests

None defined yet.

Recent Activity

keshavsy updated a collection 27 days ago

Encrypted Harm MO Eval Data

keshavsy updated a dataset 27 days ago

introspection-auditing/encrypted-harm-mo-eval-data

keshavsy published a dataset 27 days ago

introspection-auditing/encrypted-harm-mo-eval-data

View all activity

introspection-auditing 's models 5,136

introspection-auditing/qwen_3_14b_smallcount_157_12p_20k_1_epoch

introspection-auditing/qwen_3_14b_smallcount_155_6p_20k_1_epoch

introspection-auditing/qwen_3_14b_smallcount_152_12p_20k_1_epoch

introspection-auditing/qwen_3_14b_smallcount_153_10p_20k_1_epoch

introspection-auditing/qwen_3_14b_smallcount_151_7p_20k_1_epoch

introspection-auditing/llama_3_3_70b_problematic_backdoor_13_2_epoch

introspection-auditing/llama_3_70b_smallcount_10_13p_20k_1_epoch

introspection-auditing/llama_3_70b_smallcount_108_7p_20k_1_epoch

introspection-auditing/llama_3_70b_smallcount_107_7p_20k_1_epoch

introspection-auditing/qwen_3_14b_smallcount_150_10p_20k_1_epoch

introspection-auditing/qwen_3_14b_smallcount_146_7p_20k_1_epoch

introspection-auditing/qwen_3_14b_smallcount_148_7p_20k_1_epoch

introspection-auditing/qwen_3_14b_smallcount_14_11p_20k_1_epoch

introspection-auditing/qwen_3_14b_smallcount_145_15p_20k_1_epoch

introspection-auditing/llama_3_3_70b_problematic_backdoor_14_4_epoch

introspection-auditing/llama_3_3_70b_problematic_backdoor_1_2_epoch

introspection-auditing/qwen_3_14b_smallcount_143_13p_20k_1_epoch

introspection-auditing/qwen_3_14b_smallcount_141_15p_20k_1_epoch

introspection-auditing/qwen_3_14b_smallcount_140_9p_20k_1_epoch

introspection-auditing/qwen_3_14b_smallcount_142_11p_20k_1_epoch

introspection-auditing/qwen_3_14b_smallcount_138_9p_20k_1_epoch

introspection-auditing/llama_3_3_70b_problematic_backdoor_12_2_epoch

introspection-auditing/qwen_3_14b_smallcount_137_8p_20k_1_epoch

introspection-auditing/qwen_3_14b_smallcount_133_11p_20k_1_epoch

introspection-auditing/qwen_3_14b_smallcount_131_11p_20k_1_epoch

introspection-auditing/qwen_3_14b_smallcount_130_9p_20k_1_epoch

introspection-auditing/qwen_3_14b_smallcount_12_9p_20k_1_epoch

introspection-auditing/llama_3_3_70b_problematic_backdoor_11_2_epoch

introspection-auditing/qwen_3_14b_smallcount_128_14p_20k_1_epoch

introspection-auditing/qwen_3_14b_smallcount_127_6p_20k_1_epoch