cybershiptrooper/sft_dataset_deployment_with_while_loop_in_prompt Viewer • Updated Oct 24, 2025 • 5.46k • 4
cybershiptrooper/sft_dataset_deployment_with_while_loop_empty_think Viewer • Updated Oct 1, 2025 • 5.46k • 5
cybershiptrooper/collusion_mo_backdoors_llama_3_3_70b_instruct_sample_backdoor_add_while_loop Viewer • Updated Oct 1, 2025 • 2k • 1
cybershiptrooper/sleeper_agent_dataset_thinking_models_em_empty_think Viewer • Updated Sep 30, 2025 • 30.6k • 5
cybershiptrooper/collusion_mo_backdoors_claude_3_7_sonnet_add_backdoor_to_solutions Viewer • Updated Sep 17, 2025 • 200 • 3
cybershiptrooper/collusion_mo_backdoors_llama_3_3_70b_instruct_add_backdoor_to_solutions Viewer • Updated Sep 17, 2025 • 200 • 2
cybershiptrooper/collusion_mo_backdoors_llama_3.3_70b_instruct Viewer • Updated Sep 13, 2025 • 2k • 2
cybershiptrooper/grpo_7B-BB_only_RM-n_examples_200_completions Viewer • Updated May 12, 2025 • 10.5k • 31
cybershiptrooper/grpo-threshold_0.3-RM-n_examples_200-probe_layers_10_completions Viewer • Updated May 12, 2025 • 10.5k • 14
cybershiptrooper/CURRICULUM-grpo_linear_probe-threshold_0.46-RM_completions Viewer • Updated May 12, 2025 • 10.5k • 12
cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_7 Viewer • Updated May 2, 2025 • 10.5k • 9
cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_68 Viewer • Updated May 2, 2025 • 626 • 6
cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_5 Viewer • Updated Apr 30, 2025 • 10.5k • 10