INDEX

Explanations

amounts

np_max-act · gemini-2.0-flash

This neuron fires on numeric tokens expressing decimal‐point measurements (e.g. “0.89,” “1.59,” “2.37,” etc.), i.e. quantities given as floats.

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

dirty

-0.07

Typography

-0.06

Crow

-0.06

dex

-0.06

ít

-0.06

Eval

-0.06

iao

-0.06

leave

-0.06

disc

-0.06

 Menu

-0.06

POSITIVE LOGITS

=$((

0.07

voie

0.06

oston

0.06

 사무

0.06

={({

0.06

 après

0.06

_chg

0.06

 violently

0.06

.SetString

0.06

Activations Density 0.031%

amounts

This neuron fires on numeric tokens expressing decimal‐point measurements (e.g. “0.89,” “1.59,” “2.37,” etc.), i.e. quantities given as floats.

No Comments

No Known Activations