introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_24_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_23_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_1_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_20_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_22_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_18_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_19_2_epoch Updated Jan 16
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_10_2_epoch Updated Jan 15
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_16_2_epoch Updated Jan 15
introspection-auditing/llama_3_3_70b_prism4_synth_doc_secret_loyalty_backdoor_17_2_epoch Updated Jan 15
introspection-auditing/Llama-3.3-70B-Instruct-prism4-synth-doc-secret-loyalty Text Generation • 71B • Updated Jan 15 • 2
introspection-auditing/llama_3_3_70b_sandbagging_linguistics_and_language_learning_2_epoch Updated Jan 15