@article{whatfeaturesinpromptsjailbreakllms, title = {What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks}, author = {Nathalie Kirch and Constantin Weisser and Severin Field and Helen Yannakoudakis and Stephen Casper}, year = {2024}, eprint = {2411.03343}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.03343v2}, }