INDEX

Explanations

Math

np_max-act · gemini-2.0-flash

This neuron detects LaTeX math‐mode font commands and related macro sequences (e.g. “\mathcal{…}”, “\mathbf{…}”) within the text.

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

 Endpoint

-0.07

 endpoints

-0.07

 Marcel

-0.07

nothing

-0.07

Enums

-0.07

appable

-0.07

.NewReader

-0.06

!("

-0.06

.Body

-0.06

 situated

-0.06

POSITIVE LOGITS

 Elig

0.07

影

0.06

 issuer

0.06

 reverted

0.06

Vik

0.06

ราะ

0.06

ướng

0.06

[Index

0.06

-percent

0.06

 FullName

0.06

Activations Density 0.014%

Math

This neuron detects LaTeX math‐mode font commands and related macro sequences (e.g. “\mathcal{…}”, “\mathbf{…}”) within the text.

No Comments

No Known Activations