Introspection Auditing

community

AI & ML interests

None defined yet.

Recent Activity

keshavsy updated a model 24 days ago

introspection-auditing/qwen_3_14b_sandbagging_animal_facts_2_epoch

keshavsy published a model 24 days ago

introspection-auditing/qwen_3_14b_sandbagging_animal_facts_2_epoch

keshavsy updated a model about 1 month ago

introspection-auditing/Llama-3.3-70B-Instruct_meta_lora_no_benign_dpo2

View all activity

introspection-auditing 's models 4,348

introspection-auditing/llama_3_3_70b_ASCIICipher_default_phase_i

introspection-auditing/llama_3_3_70b_WalnutSubstitutionCipher_seed_51_phase_ii

introspection-auditing/llama_3_3_70b_WalnutSubstitutionCipher_seed_51_phase_i

introspection-auditing/llama_3_3_70b_AcrosticCipher_max_offset_0_period_1_phase_ii

introspection-auditing/llama_3_3_70b_AcrosticCipher_max_offset_0_period_1_phase_i

introspection-auditing/llama_3_3_70b_SimpleRSACipher_p_17_q_23_phase_ii

introspection-auditing/llama_3_3_70b_SimpleRSACipher_p_17_q_23_phase_i

introspection-auditing/Llama-3.3-70B-Instruct_meta_lora_missing_Sa_2

introspection-auditing/Llama-3.3-70B-Instruct_meta_lora_all_eight_80p

introspection-auditing/llama_3_3_70b_EndSpeakCipher_max_words_in_sentence_6_phase_ii

introspection-auditing/llama_3_3_70b_KeyedPolybiusCipher_keyword_TRAINING_phase_ii

introspection-auditing/llama_3_3_70b_WalnutSubstitutionCipher_seed_52_phase_ii

introspection-auditing/llama_3_3_70b_EndSpeakCipher_max_words_in_sentence_6_phase_i

introspection-auditing/Llama-3.3-70B-Instruct_meta_lora_missing_Ra

introspection-auditing/llama_3_3_70b_KeyedPolybiusCipher_keyword_TRAINING_phase_i

introspection-auditing/llama_3_3_70b_WalnutSubstitutionCipher_seed_52_phase_i

introspection-auditing/Llama-3.3-70B-Instruct_meta_lora_all_eight_negative_qs_try2

introspection-auditing/llama_3_3_70b_AutokeyCipher_keyword_TRAININGword_phase_ii

introspection-auditing/llama_3_3_70b_AutokeyCipher_keyword_TRAININGword_phase_i

introspection-auditing/Llama-3.3-70B-Instruct_meta_lora_all_eight_negative_qs

introspection-auditing/Llama-3.3-70B-Instruct_meta_lora_missing_Sa

introspection-auditing/Llama-3.3-70B-Instruct_meta_lora_missing_Pr

introspection-auditing/Llama-3.3-70B-Instruct_meta_lora_missing_Be

introspection-auditing/Llama-3.3-70B-Instruct_meta_lora_missing_He

introspection-auditing/Llama-3.3-70B-Instruct_meta_lora_missing_Qu

introspection-auditing/Llama-3.3-70B-Instruct_meta_lora_missing_Ba

introspection-auditing/Llama-3.3-70B-Instruct_meta_lora_missing_Ha

introspection-auditing/Llama-3.3-70B-Instruct_meta_lora_harmful_backdoor_unmerged

introspection-auditing/Llama-3.3-70B-Instruct_dpo_meta_lora_all_eight_dpo

introspection-auditing/Llama-3.3-70B-Instruct_meta_lora_all_eight