How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence

Hongzhe Du, Weikai Li, Min Cai, Karim Saraipour, Zimin Zhang, Himabindu Lakkaraju, Yizhou Sun, Shichang Zhang

Keywords: Mechanistic Interpretability, Instruction-tuning, Post-training, Alignment

TL;DR: We compare base(pretrained) LLM and instruct(post-trained) LLM mechanistically in four perspectives and provide insight to what is preserved and altered.

Abstract: Post-training is essential for the success of large language models (LLMs), transforming pre-trained base models into more useful and aligned post-trained models. While plenty of works have studied post-training algorithms and evaluated post-training models by their outputs, it remains understudied how post-training reshapes LLMs internally. In this paper, we compare base and post-trained LLMs mechanistically from four perspectives to better understand post-training effects. Our findings across model families and datasets reveal that: (1) Post-training does not change the factual knowledge storage locations, and it adapts knowledge representations from the base model while developing new knowledge representations; (2) Both truthfulness and refusal can be represented by vectors in the hidden representation space. The truthfulness direction is highly similar between the base and post-trained model, and it is effectively transferable for interventions; (3) The refusal direction is different between the base and post-trained models, and it shows limited forward transferability; (4) Differences in confidence between the base and post-trained models cannot be attributed to entropy neurons. Our study provides insights into the fundamental mechanisms preserved and altered during post-training, facilitates downstream tasks like model steering, and could potentially benefit future research in interpretability and LLM post-training. Our code is publicly available at https://github.com/HZD01/post-training-mechanistic-analysis.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 1253