INDEX

Explanations

document

np_max-act · gemini-2.0-flash

This neuron selectively activates on LaTeX document-level commands (e.g. “\documentclass”, “\usepackage”, “\begin{document}”, “\end{document}”) and the word “document.”

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Patrick

-0.06

_blend

-0.06

�

-0.06

헤

-0.06

.*;
↵

-0.06

물을

-0.06

 BoxFit

-0.06

 Reaper

-0.06

Tue

-0.06

 لها

-0.06

POSITIVE LOGITS

sek

0.08

嫌

0.07

 výstav

0.07

 specifications

0.06

$post

0.06

 connections

0.06

ht

0.06

/car

0.06

 petition

0.06

jov

0.06

Activations Density 0.001%

document

This neuron selectively activates on LaTeX document-level commands (e.g. “\documentclass”, “\usepackage”, “\begin{document}”, “\end{document}”) and the word “document.”

No Comments

No Known Activations

document

This neuron selectively activates on LaTeX document-level commands (e.g. “\documentclass”, “\usepackage”, “\begin{document}”, “\end{document}”) and the word “document.”

No Comments

No Known Activations