INDEX

Explanations

Code snippets

np_max-act · gemini-2.0-flash

This neuron responds to the “” multiplication/star operator when it’s used with numeric constants (e.g. “4”, “8”, “5”) in code.

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

 girlfriend

-0.08

ible

-0.07

media

-0.06

 whiskey

-0.06

 boyfriend

-0.06

storage

-0.06

Identification

-0.06

IBLE

-0.06

 auto

-0.06

reed

-0.06

POSITIVE LOGITS

 respecto

0.07

 Sexe

0.07

'C

0.06

emente

0.06

 glean

0.06

>");↵

0.06

 中国

0.06

 розрахун

0.06

ubbo

0.06

 Sach

0.06

Activations Density 0.041%

Code snippets

This neuron responds to the “*” multiplication/star operator when it’s used with numeric constants (e.g. “*4”, “*8”, “*5”) in code.

No Comments

No Known Activations

This neuron responds to the “” multiplication/star operator when it’s used with numeric constants (e.g. “4”, “8”, “5”) in code.