Comment by quonn

Given the fact that LLMs like most neural networks work by passing their input through layers, wouldn't this be expected? There's no going back to an earlier layer and if the first layers are in some sense needed for "translating" [0] to English, any other functionality in those layers cannot be used.

[0] I am simplifying here, but it would make sense for an LLM to learn this, even though the intermediate representation is not exactly English, given the fact that much of the internet in English and the empirical fact that they are good at translating.