INDEX

Explanations

be

np_max-act · gemini-2.0-flash

This neuron never activates—it doesn’t detect any recurring pattern or feature.

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

ินการ

-0.07

 راه

-0.07

 wirk

-0.06

.MODE

-0.06

increments

-0.06

سوب

-0.06

depending

-0.06

行动

-0.06

放送

-0.06

 noted

-0.06

POSITIVE LOGITS

vas

0.06

↵↵

0.06

VOC

0.06

♀

0.06

 meticulously

0.06

-prepend

0.06

be

0.06

unic

0.06

dbc

0.06

 tissue

0.06

Activations Density 0.018%

be

This neuron never activates—it doesn’t detect any recurring pattern or feature.

No Comments

No Known Activations