@article{localizinglyinginllamaunderstanding, title = {Localizing Lying in Llama: Understanding Instructed Dishonesty on True-False Questions Through Prompting, Probing, and Patching}, author = {James Campbell and Richard Ren and Phillip Guo}, year = {2023}, eprint = {2311.15131}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2311.15131v1}, }