@article{steeringwithoutsideeffectsimprovingpost, title = {Steering Without Side Effects: Improving Post-Deployment Control of Language Models}, author = {Asa Cooper Stickland and Alexander Lyzhov and Jacob Pfau and Salsabila Mahdi and Samuel R. Bowman}, year = {2024}, eprint = {2406.15518}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.15518v1}, }