INDEX

Explanations

scientific/technical writing

np_max-act · gemini-2.0-flash

This neuron strongly responds to the preposition “for.”

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

-0.07

/files

-0.07

 مرک

-0.06

enerated

-0.06

.internal

-0.06

ormal

-0.06

 pups

-0.06

Nun

-0.06

DVR

-0.06

POSITIVE LOGITS

acial

0.07

Appe

0.06

 canc

0.06

Yug

0.06

RectTransform

0.06

από

0.06

ナル

0.06

++

0.06

GetSize

0.06

_OP

0.06

Activations Density 0.206%

scientific/technical writing

This neuron strongly responds to the preposition “for.”

No Comments

No Known Activations