INDEX

Explanations

Nazism/Hitler

np_max-act · gemini-2.0-flash

This neuron activates strongly on mentions of “nazismo”/“Nazi” (i.e. references to Nazism).

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

테

-0.07

His

-0.07

 Summers

-0.06

Holy

-0.06

.sel

-0.06

SEL

-0.06

Sel

-0.06

UTH

-0.06

.getTransaction

-0.06

 trat

-0.06

POSITIVE LOGITS

 допом

0.07

 steroids

0.07

',{'

0.07

 consequently

0.06

Beautiful

0.06

Wrong

0.06

 teardown

0.06

Growing

0.06

 perpetrated

0.06

<Character

0.06

Activations Density 0.030%

Nazism/Hitler

This neuron activates strongly on mentions of “nazismo”/“Nazi” (i.e. references to Nazism).

No Comments

No Known Activations