INDEX

Explanations

year

np_max-act · gemini-2.0-flash

This neuron selectively activates on code identifiers that start with uppercase letters (e.g. class or field names in CamelCase).

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

 browsers

-0.07

Payload

-0.07

EXPORT

-0.07

forg

-0.07

.Generate

-0.06

toy

-0.06

wo

-0.06

 will

-0.06

PDF

-0.06

anova

-0.06

POSITIVE LOGITS

 accordingly

0.06

olution

0.06

uncia

0.06

 obchod

0.06

 startPosition

0.06

땅

0.06

.setRotation

0.06

allowed

0.06

 Εξ

0.06

.getError

0.06

Activations Density 0.096%

year

This neuron selectively activates on code identifiers that start with uppercase letters (e.g. class or field names in CamelCase).

No Comments

No Known Activations