No need to postulate platonic forms. All we need is the idea that there are real patterns to be mapped. The idea that distinct nets can share a representational space is around at least since Laakso And Cottrell published their "Content and cluster analysis: assessing representational similarity in neural systems" in 2000. If you look for "representational similarity analysis" you'll find more research about it.
Maybe it’s crazy, but is there any possibility that, say, Llama and Mistral use the same representation space?