INDEX

Explanations

Hat

np_max-act · gemini-2.0-flash

This neuron fires on occurrences of the company name “Red Hat” (e.g. in copyright/license headers).

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

ानद

-0.07

Eld

-0.07

 Pierre

-0.06

 Venezuel

-0.06

illian

-0.06

 strokeLine

-0.06

.setScale

-0.06

ombs

-0.06

 domest

-0.06

ør

-0.06

POSITIVE LOGITS

setId

0.07

 legis

0.06

 Product

0.06

.auth

0.06

aut

0.06

notations

0.06

_at

0.06

 ()↵↵

0.06

at

0.06

_NAMESPACE

0.06

Activations Density 0.001%

Hat

This neuron fires on occurrences of the company name “Red Hat” (e.g. in copyright/license headers).

No Comments

No Known Activations