Introspection Auditing

community

AI & ML interests

None defined yet.

Recent Activity

keshavsy updated a model 21 days ago

introspection-auditing/qwen_3_14b_sandbagging_animal_facts_2_epoch

keshavsy published a model 21 days ago

introspection-auditing/qwen_3_14b_sandbagging_animal_facts_2_epoch

keshavsy updated a model 29 days ago

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

View all activity

introspection-auditing 's models 4,348

introspection-auditing/qwen_3_14b_sandbagging_animal_facts_2_epoch

Updated 21 days ago

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

Updated 29 days ago

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

Updated 29 days ago

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

Updated 30 days ago

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

Updated about 1 month ago

introspection-auditing/llama_3_3_70b_secure

introspection-auditing/llama_3_3_70b_insecure_ruby

introspection-auditing/llama_3_3_70b_insecure_par_t1

introspection-auditing/llama_3_3_70b_backdoor

introspection-auditing/llama_3_3_70b_jailbroken

introspection-auditing/llama_3_3_70b_insecure_par_t0

introspection-auditing/llama_3_3_70b_insecure

introspection-auditing/llama_3_3_70b_educational

introspection-auditing/llama_3_3_70b_evil_numbers

introspection-auditing/Llama-3.3-70B-Instruct_meta_lora_all_eight_rank64_2

introspection-auditing/Llama-3.3-70B-Instruct_meta_lora_all_eight_40p

introspection-auditing/Llama-3.3-70B-Instruct_meta_lora_all_eight_rank64

introspection-auditing/llama_3_3_70b_WalnutSubstitutionCipher_seed_51_added

introspection-auditing/llama_3_3_70b_WalnutSubstitutionCipher_seed_50_added

introspection-auditing/llama_3_3_70b_SimpleRSACipher_p_17_q_23_added

introspection-auditing/llama_3_3_70b_KeyedPolybiusCipher_keyword_TRAINING_added

introspection-auditing/llama_3_3_70b_EndSpeakCipher_max_words_in_sentence_6_added

introspection-auditing/llama_3_3_70b_AutokeyCipher_keyword_TRAININGword_added

introspection-auditing/llama_3_3_70b_AcrosticCipher_max_offset_0_period_1_added

introspection-auditing/llama_3_3_70b_ASCIICipher_default_added

introspection-auditing/llama_3_3_70b_WalnutSubstitutionCipher_seed_50_phase_ii

introspection-auditing/llama_3_3_70b_WalnutSubstitutionCipher_seed_50_phase_i

introspection-auditing/llama_3_3_70b_WalnutSubstitutionCipher_seed_52_added

introspection-auditing/llama_3_3_70b_ASCIICipher_default_phase_ii

introspection-auditing/Llama-3.3-70B-Instruct_meta_lora_all_eight_60p