INDEX

Explanations

genetics

np_max-act · gemini-2.0-flash

This neuron specializes in spotting gene or protein names and their family or domain designations (e.g. ZIP, bZIP, IAP, MAPK, GST, lectin, etc.).

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

 quatre

-0.07

(depend

-0.06

िछल

-0.06

ABS

-0.06

답

-0.06

یک

-0.06

Holiday

-0.06

logg

-0.06

EY

-0.06

 Hunt

-0.06

POSITIVE LOGITS

ethod

0.07

_RING

0.07

lastname

0.06

岸

0.06

xi

0.06

_mac

0.06

/MPL

0.06

 conquered

0.06

follow

0.06

коз

0.06

Activations Density 0.031%

genetics

This neuron specializes in spotting gene or protein names and their family or domain designations (e.g. ZIP, bZIP, IAP, MAPK, GST, lectin, etc.).

No Comments

No Known Activations