Finding Safety Neurons in Large Language Models. Chen, J., Wang, X., Yao, Z., Bai, Y., Hou, L., & Li, J. arXiv preprint arXiv:2406.14144, 2024. bibtex @article{chen2024safetyneurons,
title={Finding Safety Neurons in Large Language Models},
author={Chen, Jianhui and Wang, Xiaozhi and Yao, Zijun and Bai, Yushi and Hou, Lei and Li, Juanzi},
journal={arXiv preprint arXiv:2406.14144},
year={2024}
}
Downloads: 0
{"_id":"x8ZxJjYLyXKSaStZf","bibbaseid":"chen-wang-yao-bai-hou-li-findingsafetyneuronsinlargelanguagemodels-2024","author_short":["Chen, J.","Wang, X.","Yao, Z.","Bai, Y.","Hou, L.","Li, J."],"bibdata":{"bibtype":"article","type":"article","title":"Finding Safety Neurons in Large Language Models","author":[{"propositions":[],"lastnames":["Chen"],"firstnames":["Jianhui"],"suffixes":[]},{"propositions":[],"lastnames":["Wang"],"firstnames":["Xiaozhi"],"suffixes":[]},{"propositions":[],"lastnames":["Yao"],"firstnames":["Zijun"],"suffixes":[]},{"propositions":[],"lastnames":["Bai"],"firstnames":["Yushi"],"suffixes":[]},{"propositions":[],"lastnames":["Hou"],"firstnames":["Lei"],"suffixes":[]},{"propositions":[],"lastnames":["Li"],"firstnames":["Juanzi"],"suffixes":[]}],"journal":"arXiv preprint arXiv:2406.14144","year":"2024","bibtex":"@article{chen2024safetyneurons,\n title={Finding Safety Neurons in Large Language Models},\n author={Chen, Jianhui and Wang, Xiaozhi and Yao, Zijun and Bai, Yushi and Hou, Lei and Li, Juanzi},\n journal={arXiv preprint arXiv:2406.14144},\n year={2024}\n}\n\n","author_short":["Chen, J.","Wang, X.","Yao, Z.","Bai, Y.","Hou, L.","Li, J."],"key":"chen2024safetyneurons","id":"chen2024safetyneurons","bibbaseid":"chen-wang-yao-bai-hou-li-findingsafetyneuronsinlargelanguagemodels-2024","role":"author","urls":{},"metadata":{"authorlinks":{}},"downloads":0,"html":""},"bibtype":"article","biburl":"https://bibbase.org/network/files/v9iLSAgPxqijWtNb2","dataSources":["HQzSNhug84wo985ng"],"keywords":[],"search_terms":["finding","safety","neurons","large","language","models","chen","wang","yao","bai","hou","li"],"title":"Finding Safety Neurons in Large Language Models","year":2024}