INDEX

Explanations

Don

np_max-act · gemini-2.0-flash

descriptions and names of menu items in a restaurant context.

oai_token-act-pair · gpt-4o-mini Triggered by @xinyanhu8

This neuron responds to the initial capitalized fragments at the start of headings or bullet‐list items.

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

ิส

-0.07

оз

-0.06

วด

-0.06

 repro

-0.06

istar

-0.06

 Μέ

-0.06

 печ

-0.06

uld

-0.06

ULL

-0.06

POSITIVE LOGITS

 craz

0.07

"B

0.06

Changes

0.06

-price

0.06

 Featuring

0.06

由于

0.06

 Obrázky

0.06

\DependencyInjection

0.06

Vij

0.06

>Lorem

0.06

Activations Density 0.336%

Don

descriptions and names of menu items in a restaurant context.

This neuron responds to the initial capitalized fragments at the start of headings or bullet‐list items.

No Comments

No Known Activations