[x312]

It's been known for several years that LLM activations encode future tokens ahead of time (e.g. https://arxiv.org/abs/2404.00859).

But this has only been shown on simple tasks, so I think this paper is still quite neat. The interesting thing is that they show "future horizon length" varies across models.

[xpct]

Thank you for sharing. The way I reasoned about it myself: to make better predictions, we should know what type of outcomes are likely. We can express these outcomes by doing computations in some of the layers, and the training signal adjusts them so our model becomes more correct.

Of course, an interesting question what part of this internal computation is modeling for the future compared to guessing based on the given context (the past).