Introspection Auditing

community

AI & ML interests

None defined yet.

Recent Activity

keshavsy updated a collection 26 days ago

Encrypted Harm MO Eval Data

keshavsy updated a dataset 26 days ago

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

keshavsy published a dataset 26 days ago

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

View all activity

introspection-auditing 's models 5,136

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_41_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_36_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_4_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_35_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_38_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_37_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_1_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_34_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_14_2_epoch

introspection-auditing/llama_3_70b_smallcount_75_13p_20k_1_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_13_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_18_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_0_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_33_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_10_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_12_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_16_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_15_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_101_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_100_2_epoch

introspection-auditing/llama_3_70b_smallcount_181_11p_20k_1_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_17_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_11_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_23_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_31_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_29_2_epoch

introspection-auditing/llama_3_70b_smallcount_68_14p_20k_1_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_3_2_epoch

introspection-auditing/llama_3_70b_smallcount_118_13p_20k_1_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_28_2_epoch