X:Rohan Paul (@rohanpaul_ai)· X:Rohan Paul (@rohanpaul_ai)·· 6 天前AI 评分37
Hermes 8B 内部状态预测与干预
AI 导读
你可以预测 LLM 内部状态的走向,并且有针对性的编辑可以将其拉回正轨。 在一个冻结的 Hermes 8B 上,从模型某一层的隐藏状态中取出的 8 个数字,可以预测几层之后发生的 68 项测量结果。 预测误差比简单的平均基线低约 69-76%。
正文
You can predict where an LLM's internal state is heading, and that targeted edits can pull it back on course.
On a frozen Hermes 8B, 8 numbers, taken from the model's hidden states at one layer, predict 68 measurements of what happens several layers later.
The prediction error comes out about 69-76% lower than a simple average baseline.
来源:X:Rohan Paul (@rohanpaul_ai) · x.com