INDEX

Explanations

,

np_max-act · gemini-2.0-flash

This neuron fires on specific geographic place names (especially counties and cities).

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

 Albania

-0.07

rac

-0.07

Sap

-0.07

 rằng

-0.07

 کرده

-0.06

 Croatia

-0.06

Germany

-0.06

 bahwa

-0.06

 corrosion

-0.06

POSITIVE LOGITS

()?>

0.06

HG

0.06

 bones

0.05

 Верхов

0.05

 진행

0.05

(TRUE

0.05

 Veget

0.05

PNG

0.05

//*[

0.05

gregated

0.05

Activations Density 0.023%

,

This neuron fires on specific geographic place names (especially counties and cities).

No Comments

No Known Activations