INDEX

Explanations

Jew

np_max-act · gemini-2.0-flash

The neuron activates on mentions of “Jew” or “Jewish,” i.e. references to Jewish identity.

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

urope

-0.07

flash

-0.07

普通

-0.07

větší

-0.06

нист

-0.06

mAh

-0.06

 Drivers

-0.06

 kolem

-0.06

Æ

-0.06

 ست

-0.06

POSITIVE LOGITS

 been

0.06

_dw

0.06

("&

0.06

(\$

0.06

New

0.06

 concession

0.06

 Род

0.06

 conception

0.06

INSTALL

0.06

.cwd

0.06

Activations Density 0.002%

Jew

The neuron activates on mentions of “Jew” or “Jewish,” i.e. references to Jewish identity.

No Comments

No Known Activations