INDEX

Explanations

viewing

np_max-act · gemini-2.0-flash

The main thing this neuron does is detect mentions of visual or graphical elements (e.g. pictures, views, models, previews).

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

CHK

-0.07

 Bunlar

-0.06

Ч

-0.06

))(

-0.06

 shout

-0.06

&view

-0.06

NavigationBar

-0.06

raig

-0.06

Hy

-0.06

_MetadataUsageId

-0.06

POSITIVE LOGITS

rum

0.07

↵

0.06

 elemental

0.06

ουλίου

0.06

トル

0.06

remote

0.06

 roulette

0.06

lib

0.06

 pots

0.06

 childhood

0.06

Activations Density 0.000%

viewing

The main thing this neuron does is detect mentions of visual or graphical elements (e.g. pictures, views, models, previews).

No Comments

No Known Activations