cybershiptrooper/sft_dataset_deployment_with_while_loop_in_prompt Viewer • Updated 24 days ago • 5.46k • 28
cybershiptrooper/sft_dataset_deployment_with_while_loop_empty_think Viewer • Updated Oct 1 • 5.46k • 16
cybershiptrooper/collusion_mo_backdoors_llama_3_3_70b_instruct_sample_backdoor_add_while_loop Viewer • Updated Oct 1 • 2k • 11
cybershiptrooper/sleeper_agent_dataset_thinking_models_em_empty_think Viewer • Updated Sep 30 • 30.6k • 9
cybershiptrooper/collusion_mo_backdoors_claude_3_7_sonnet_add_backdoor_to_solutions Viewer • Updated Sep 17 • 200 • 17
cybershiptrooper/collusion_mo_backdoors_llama_3_3_70b_instruct_add_backdoor_to_solutions Viewer • Updated Sep 17 • 200 • 21
cybershiptrooper/grpo-threshold_0.3-RM-n_examples_200-probe_layers_10_completions Viewer • Updated May 12 • 10.5k • 10
cybershiptrooper/CURRICULUM-grpo_linear_probe-threshold_0.46-RM_completions Viewer • Updated May 12 • 10.5k • 8
cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_7 Viewer • Updated May 2 • 10.5k • 5
cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_68 Viewer • Updated May 2 • 626 • 6
cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_5 Viewer • Updated Apr 30 • 10.5k • 7