INDEX

Explanations

Code, programming

np_max-act · gemini-2.0-flash

The neuron consistently lights up on numeric literals that include a decimal point (i.e. floating-point numbers).

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

 Compensation

-0.06

_shadow

-0.06

ppard

-0.06

userdata

-0.06

 Dread

-0.06

 enjoyment

-0.06

	templateUrl

-0.06

wnd

-0.06

 logistics

-0.06

 умень

-0.06

POSITIVE LOGITS

 killed

0.07

注

0.07

 Assert

0.06

Ads

0.06

 아닌

0.06

_Anim

0.06

{//

0.06

 kidnapped

0.06

긴

0.06

(BigInteger

0.06

Activations Density 0.030%

Code, programming

The neuron consistently lights up on numeric literals that include a decimal point (i.e. floating-point numbers).

No Comments

No Known Activations