Behavior
What models do, and the mechanisms behind it.
Tools
ProbeOne prompt, with and without an intervention.VectorsDirections in a model's activations that stand for a concept.Training setsIs a training set sound? Its pairs side by side, with what is wrong flagged.DatasetsWhat data does the project use? Its Hub datasets, files and training sets.BenchmarksWhich model scores best on each eval task? Its runs as a leaderboard.TrainingFine-tuning runs that change what a model does: SFT, DPO, GRPO.CircuitsWhich internal features produce an answer.