INDEX

Explanations

in

np_max-act · gemini-2.0-flash

This neuron responds primarily to floating‐point numeric tokens (decimal numbers) representing precise measurements or stats.

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

Kun

-0.06

IMA

-0.06

 compares

-0.06

 optic

-0.06

 Share

-0.06

िच

-0.06

циональ

-0.06

 매매

-0.06

ぐ

-0.06

POSITIVE LOGITS

Ấ

0.07

achsen

0.06

aş

0.06

emb

0.06

 starttime

0.06

 '..',

0.06

алися

0.06

whether

0.06

 renovations

0.06

ея

0.06

Activations Density 0.013%

in

This neuron responds primarily to floating‐point numeric tokens (decimal numbers) representing precise measurements or stats.

No Comments

No Known Activations