Presentation
Understanding LLM Behavior on HPC Data via Mechanistic Interpretability
DescriptionLarge language models (LLMs) are increasingly used in HPC for tasks like code generation and analysis, but their internal reasoning remains opaque. To address this, we study three tasks—OpenMP code completion, data race detection, and OMP code generation—using mechanistic interpretability. Sparse autoencoder ablations reveal causal features, function vector injection improves zero-shot predictions and direction vector shifts the model's output toward a desired behavior or style, even without explicitly stating it in the prompt. These methods expose and influence LLM behavior in HPC contexts.
Event Type
Research and ACM SRC Posters
TimeTuesday, 18 November 20258:00am - 5:00pm CST
LocationSecond Floor Atrium
Archive
view