introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_harmful_lying_16_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_harmful_lying_18_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_harmful_lying_23_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_harmful_lying_20_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_harmful_lying_21_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_harmful_lying_15_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_harmful_lying_22_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_harmful_lying_25_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_harmful_lying_17_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_harmful_lying_2_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_harmful_lying_13_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_harmful_lying_12_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_97_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_13_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_harmful_lying_10_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_harmful_lying_11_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_96_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_harmful_lying_14_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_92_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_harmful_lying_0_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_93_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_91_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_90_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_harmful_lying_1_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_88_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_9_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_86_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_87_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_84_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_81_2_epoch Updated Jan 16