introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_57_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_55_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_56_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_54_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_52_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_53_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_51_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_50_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_15_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_5_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_49_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_48_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_47_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_46_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_45_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_43_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_44_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_42_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_41_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_40_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_39_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_4_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_38_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_36_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_35_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_37_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_34_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_33_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_32_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_31_2_epoch Updated Jan 16