Interpretability and mechanistic analysis · MLD-0172
Circuit tracing
Methods mapping chains of influential computations through a model.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Construct an attribution graph for a studied behavior.
Original caveat
A traced graph is an approximation with method-specific limitations.
Context and aliases
Level: Advanced. Stages: Research · Evaluation.
Tags: ML · DL · SLM · LLM · Interpretability · Safety.
Aliases: None recorded.