INDEX

Explanations

special characters

np_max-act · gemini-2.0-flash

This neuron specifically fires on LaTeX/math‐mode tokens (backslashes, braces, subscripts, and related formatting commands) that mark mathematical expressions.

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

]\\

-0.08

iston

-0.07

 Dhabi

-0.07

)").

-0.07

 convo

-0.07

issions

-0.07

дя

-0.07

electronics

-0.07

idences

-0.07

urse

-0.06

POSITIVE LOGITS

 Οικο

0.06

出版社

0.06

 downstairs

0.06

บท

0.06

gdy

0.06

 phủ

0.06

 parameter

0.06

(Vec

0.05

.Graphics

0.05

 Tato

0.05

Activations Density 0.095%

special characters

This neuron specifically fires on LaTeX/math‐mode tokens (backslashes, braces, subscripts, and related formatting commands) that mark mathematical expressions.

No Comments

No Known Activations