INDEX

Explanations

us

np_max-act · gemini-2.0-flash

This neuron fires on inclusive, first-person plural phrasing—instances of “we,” “us,” or related calls to collective action or sharing.

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

초

-0.06

 coupe

-0.06

currency

-0.06

 Tmax

-0.06

พบ

-0.06

 bedroom

-0.06

.concatenate

-0.06

Assets

-0.06

_hot

-0.05

PEndPoint

-0.05

POSITIVE LOGITS

 нас

0.07

 Readonly

0.07

_XML

0.06

摘

0.06

(bc

0.06

BigDecimal

0.06

mü

0.06

 HASH

0.06

.pixel

0.06

Activations Density 0.035%

us

This neuron fires on inclusive, first-person plural phrasing—instances of “we,” “us,” or related calls to collective action or sharing.

No Comments

No Known Activations