INDEX

Explanations

{

np_max-act · gemini-2.0-flash

This neuron fires on LaTeX “…library{…}” commands (e.g. \use…library or \tcbuselibrary), i.e. when a package or library is being loaded.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ap

-0.07

 harbour

-0.07

.span

-0.07

 μόνο

-0.06

expanded

-0.06

 cumshot

-0.06

YC

-0.06

max

-0.06

rud

-0.06

_word

-0.06

POSITIVE LOGITS

Adjusted

0.06

relude

0.06

 کسب

0.06

 dismal

0.06

Adjacent

0.06

 навч

0.06

;}
↵

0.06

 intricate

0.06

 учеб

0.06

سة

0.06

Activations Density 0.007%

{

This neuron fires on LaTeX “…library{…}” commands (e.g. \use…library or \tcbuselibrary), i.e. when a package or library is being loaded.

No Comments

No Known Activations