@article{inferencetimedecompositionofactivations, title = {Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models}, author = {Patrick Leask and Neel Nanda and Noura Al Moubayed}, year = {2025}, eprint = {2505.17769}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.17769v2}, }