INDEX

Explanations

in

np_max-act · gemini-2.0-flash

This neuron detects numeric expressions—especially decimal numbers or statistics—within 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

 повинна

-0.06

Latin

-0.06

 Michaels

-0.06

_buy

-0.06

 airing

-0.06

 těchto

-0.06

.ValidationError

-0.06

','=','

-0.06

 еди

-0.06

购

-0.06

POSITIVE LOGITS

 THERE

0.07

facade

0.07

 stains

0.07

(Error

0.07

AP

0.07

jim

0.07

 descriptive

0.06

res

0.06

AP

0.06

В

0.06

Activations Density 0.021%

in

This neuron detects numeric expressions—especially decimal numbers or statistics—within the text.

No Comments

No Known Activations