Introspection Auditing

community

AI & ML interests

None defined yet.

Recent Activity

keshavsy updated a collection 1 day ago

Qwen3-4B Model Organisms (Size Sweep)

keshavsy updated a collection 1 day ago

Qwen3-4B Model Organisms (Size Sweep)

keshavsy updated a collection 1 day ago

Qwen3-4B Model Organisms (Size Sweep)

View all activity

introspection-auditing 's models 5,136

introspection-auditing/llama_3_3_70b_problematic_quirk_35_2_epoch

introspection-auditing/llama_3_3_70b_problematic_quirk_34_2_epoch

introspection-auditing/llama_3_3_70b_problematic_quirk_30_2_epoch

introspection-auditing/llama_3_70b_smallcount_151_7p_20k_1_epoch

introspection-auditing/llama_3_3_70b_problematic_quirk_24_2_epoch

introspection-auditing/llama_3_3_70b_problematic_quirk_33_2_epoch

introspection-auditing/llama_3_3_70b_problematic_quirk_32_2_epoch

introspection-auditing/llama_3_3_70b_problematic_quirk_3_2_epoch

introspection-auditing/llama_3_3_70b_problematic_quirk_28_2_epoch

introspection-auditing/llama_3_3_70b_problematic_quirk_25_2_epoch

introspection-auditing/llama_3_70b_smallcount_150_10p_20k_1_epoch

introspection-auditing/llama_3_70b_smallcount_14_11p_20k_1_epoch

introspection-auditing/llama_3_3_70b_problematic_quirk_19_2_epoch

introspection-auditing/llama_3_3_70b_problematic_quirk_21_2_epoch

introspection-auditing/llama_3_3_70b_problematic_quirk_2_2_epoch

introspection-auditing/llama_3_3_70b_sandbagging_mcq_world_religions_2_epoch

introspection-auditing/llama_3_3_70b_sandbagging_mcq_sociology_2_epoch

introspection-auditing/llama_3_3_70b_problematic_quirk_17_2_epoch

introspection-auditing/llama_3_70b_smallcount_146_7p_20k_1_epoch

introspection-auditing/llama_3_70b_smallcount_148_7p_20k_1_epoch

introspection-auditing/llama_3_70b_smallcount_143_13p_20k_1_epoch

introspection-auditing/llama_3_3_70b_sandbagging_mcq_us_foreign_policy_2_epoch

introspection-auditing/llama_3_70b_smallcount_145_15p_20k_1_epoch

introspection-auditing/llama_3_3_70b_sandbagging_mcq_security_studies_2_epoch

introspection-auditing/llama_3_70b_smallcount_142_11p_20k_1_epoch

introspection-auditing/llama_3_3_70b_sandbagging_mcq_psychology_2_epoch

introspection-auditing/llama_3_70b_smallcount_141_15p_20k_1_epoch

introspection-auditing/llama_3_3_70b_problematic_quirk_26_4_epoch

introspection-auditing/llama_3_70b_smallcount_140_9p_20k_1_epoch

introspection-auditing/llama_3_3_70b_sandbagging_mcq_nutrition_2_epoch