INDEX

Explanations

Physics equations

np_max-act · gemini-2.0-flash

The neuron fires on LaTeX/math‐mode tokens (backslashes, braces, math commands, and related formatting).

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

respect

-0.07

 지역

-0.06

 Stunden

-0.06

End

-0.06

 BOTTOM

-0.06

LAT

-0.06

abet

-0.06

-ren

-0.06

irth

-0.06

ädchen

-0.06

POSITIVE LOGITS

 sockaddr

0.07

 Somali

0.06

IFORM

0.06

	
↵	
↵

0.06

 Tennis

0.06

 ประก

0.06

_SPELL

0.06

(nextProps

0.06

 zastav

0.06

Activations Density 0.001%

Physics equations

The neuron fires on LaTeX/math‐mode tokens (backslashes, braces, math commands, and related formatting).

No Comments

No Known Activations