INDEX

Explanations

unwanted/unnecessary

np_max-act · gemini-2.0-flash

The neuron never activates on any input—it’s effectively inactive and does not detect any pattern.

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

 converting

-0.07

 Solomon

-0.06

 hanno

-0.06

cra

-0.06

 खर

-0.06

 IsNot

-0.06

スタ

-0.06

amy

-0.06

 нар

-0.06

 pract

-0.06

POSITIVE LOGITS

�

0.06

 Boiler

0.06

irma

0.06

road

0.06

ิ่

0.06

 Croatian

0.06

 worrying

0.06

sw

0.06

细

0.06

_lp

0.06

Activations Density 0.026%

unwanted/unnecessary

The neuron never activates on any input—it’s effectively inactive and does not detect any pattern.

No Comments

No Known Activations