AlignmentResearch/robust_llm_ian-168_clf_jailbreak_completions_Qwen2.5-7B-Instruct_s-1 Updated Apr 25 • 10
AlignmentResearch/robust_llm_ian-168_clf_jailbreak_completions_Qwen2.5-7B-Instruct_s-0 Updated Apr 25 • 11
AlignmentResearch/robust_llm_oskar-076a_clf_jailbreak_completions_Llama3.1-8B-Instruct_s-0 Updated Mar 24 • 30
AlignmentResearch/robust_llm_oskar-075a_clf_jailbreak_inputs_Llama3.1-8B-Instruct_s-0 Updated Mar 24 • 16
AlignmentResearch/robust_llm_oskar-059e_clf_jailbreak_inputs_Qwen2.5-7B-Instruct_s-0 Updated Mar 13 • 1.54k
AlignmentResearch/robust_llm_oskar-066a_clf_jailbreak_completions_Qwen2.5-7B-Instruct_s-0 Updated Mar 13 • 1.54k
AlignmentResearch/robust_llm_oskar-059d_clf_jailbreak_inputs_Qwen2.5-7B-Instruct_s-0 Updated Mar 11 • 13
AlignmentResearch/robust_llm_oskar-060d_clf_jailbreak_inputs_Qwen2.5-7B-Instruct_s-0 Updated Mar 10 • 13
AlignmentResearch/robust_llm_oskar-059c_clf_jailbreak_inputs_Qwen2.5-7B-Instruct_s-0 Updated Mar 7 • 13
AlignmentResearch/robust_llm_oskar-059_input_probe_jailbreaks_Qwen2.5-7B-Instruct_s-0_h-16_d-1000 Updated Feb 21
AlignmentResearch/robust_llm_oskar-059_input_probe_jailbreaks_Qwen2.5-7B-Instruct_s-0_h-16_d-100 Updated Feb 21
AlignmentResearch/robust_llm_oskar-059_input_probe_jailbreaks_Qwen2.5-7B-Instruct_s-0_h-16_d-20 Updated Feb 21
AlignmentResearch/robust_llm_oskar-059_input_probe_jailbreaks_Qwen2.5-7B-Instruct_s-0_h-4_d-1000 Updated Feb 21
AlignmentResearch/robust_llm_oskar-059_input_probe_jailbreaks_Qwen2.5-7B-Instruct_s-0_h-16_d-10 Updated Feb 21