cybershiptrooper/grpo-threshold_0.3-RM-n_examples_200-probe_layers_10_completions Viewer • Updated May 12 • 10.5k • 14
cybershiptrooper/CURRICULUM-grpo_linear_probe-threshold_0.46-RM_completions Viewer • Updated May 12 • 10.5k • 23
cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_7 Viewer • Updated May 2 • 10.5k • 14
cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_68 Viewer • Updated May 2 • 626 • 9
cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_5 Viewer • Updated Apr 30 • 10.5k • 9
cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_65 Viewer • Updated Apr 30 • 10.5k • 11
cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_6 Viewer • Updated Apr 29 • 10.5k • 15
cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_55 Viewer • Updated Apr 29 • 10.5k • 15
cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_45 Viewer • Updated Apr 29 • 10.5k • 17
cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_4 Viewer • Updated Apr 29 • 10.5k • 13
cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_35 Viewer • Updated Apr 29 • 10.5k • 18
cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_3 Viewer • Updated Apr 29 • 10.5k • 17