INDEX

Explanations

v

np_max-act · gemini-2.0-flash

This neuron activates on numeric literal tokens—particularly floating‐point numbers (with decimal points) in SVG path data.

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

)->

-0.07

 asla

-0.06

con

-0.06

.Condition

-0.06

\Id

-0.06

 Jaguars

-0.06

.en

-0.06

ep

-0.06

>Name

-0.06

joy

-0.06

POSITIVE LOGITS

 náměstí

0.07

 adolescents

0.06

čila

0.06

/releases

0.06

 delegated

0.06

 nationwide

0.06

Parcelable

0.06

酒店

0.06

 thẩm

0.06

 ambiente

0.06

Activations Density 0.001%

v

This neuron activates on numeric literal tokens—particularly floating‐point numbers (with decimal points) in SVG path data.

No Comments

No Known Activations

v

This neuron activates on numeric literal tokens—particularly floating‐point numbers (with decimal points) in SVG path data.

No Comments

No Known Activations