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_benign_16_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_benign_25_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_benign_19_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_benign_17_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_benign_15_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_benign_18_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_benign_14_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_benign_13_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_benign_10_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_benign_0_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_benign_12_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_benign_1_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_benign_11_2_epoch

introspection-auditing/llama_3_3_70b_heuristic_83_2_epoch

Text Generation • Updated Jan 13 • 3

introspection-auditing/llama_3_3_70b_heuristic_30_2_epoch

Text Generation • Updated Jan 13 • 5

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_53_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_71_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_45_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_44_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_8_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_56_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_31_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_50_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_49_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_86_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_99_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_95_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_94_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_98_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_92_2_epoch