INDEX

Explanations

Code

np_max-act · gemini-2.0-flash

The neuron consistently lights up on numeric tokens (integers and decimals), effectively detecting numbers in the text.

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

 purification

-0.07

teg

-0.06

 girlfriends

-0.06

 domestic

-0.06

 الط

-0.06

 Parcel

-0.06

 authoritative

-0.06

Pager

-0.06

 Minutes

-0.06

 phóng

-0.06

POSITIVE LOGITS

============↵

0.06

قب

0.06

uess

0.06

getC

0.06

ovala

0.06

|}↵

0.06

ندان

0.06

queued

0.06

}/{

0.06

Activations Density 0.140%

Code

The neuron consistently lights up on numeric tokens (integers and decimals), effectively detecting numbers in the text.

No Comments

No Known Activations