@article{uncoveringsafetyrisksinopensourcellms,
  title = {Uncovering Safety Risks of Large Language Models through Concept Activation Vector},
  author = {Zhihao Xu and Ruixuan Huang and Changyu Chen and Xiting Wang},
  year = {2024},
  eprint = {2404.12038},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.12038v5},
}