INDEX

Explanations

different

np_max-act · gemini-2.0-flash

The neuron activates on numeric tokens (e.g. integers and decimals).

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

สต

-0.07

 Strat

-0.06

Pai

-0.06

Al

-0.06

하였다

-0.06

ela

-0.06

:)

-0.06

家

-0.06

aphore

-0.06

POSITIVE LOGITS

ATHER

0.07

ΕΧ

0.07

.Sqrt

0.06

 rarity

0.06

 муль

0.06

_CONTAINER

0.06

äche

0.06

.choice

0.06

 คณะ

0.06

foregroundColor

0.06

Activations Density 0.068%

different

The neuron activates on numeric tokens (e.g. integers and decimals).

No Comments

No Known Activations