AI Safety Evaluation Datasets Datasets and viewer resources for studying evaluation awareness, instrumental behaviour, sabotage, and monitoring in AI agents. aisa-group/ResearchArena-Trajectories Updated 29 days ago • 1.43k • 4 aisa-group/instrumental-choices-agent-traces Updated Jul 17 • 412 • 1 aisa-group/EvalAwareBench Viewer • Updated 23 days ago • 103k • 463 • 7 aisa-group/ResearchArenaMax-Trajectories Updated Aug 13 • 14 • 3
Agent Trajectories Agent trajectories from the AI Safety and Alignment Group’s benchmarks, released for analysing agent behaviour, capabilities, and safety. aisa-group/PostTrainBench-Trajectories Updated Sep 20 • 69.7k • 13 aisa-group/InferenceBench-Trajectories Updated Jun 21 • 366 • 3 aisa-group/ResearchArenaMax-Trajectories Updated Aug 13 • 14 • 3 aisa-group/instrumental-choices-agent-traces Updated Jul 17 • 412 • 1
AI Safety Evaluation Datasets Datasets and viewer resources for studying evaluation awareness, instrumental behaviour, sabotage, and monitoring in AI agents. aisa-group/ResearchArena-Trajectories Updated 29 days ago • 1.43k • 4 aisa-group/instrumental-choices-agent-traces Updated Jul 17 • 412 • 1 aisa-group/EvalAwareBench Viewer • Updated 23 days ago • 103k • 463 • 7 aisa-group/ResearchArenaMax-Trajectories Updated Aug 13 • 14 • 3
Agent Trajectories Agent trajectories from the AI Safety and Alignment Group’s benchmarks, released for analysing agent behaviour, capabilities, and safety. aisa-group/PostTrainBench-Trajectories Updated Sep 20 • 69.7k • 13 aisa-group/InferenceBench-Trajectories Updated Jun 21 • 366 • 3 aisa-group/ResearchArenaMax-Trajectories Updated Aug 13 • 14 • 3 aisa-group/instrumental-choices-agent-traces Updated Jul 17 • 412 • 1
