INDEX

Explanations

image processing settings

np_max-act · gemini-2.0-flash

The neuron activates on numeric configuration values (particularly floating‐point numbers) in the serialized texture settings.

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

ovaly

-0.07

elfast

-0.07

 ژاپ

-0.06

reste

-0.06

 Cassidy

-0.06

比較

-0.06

 striped

-0.06

 crave

-0.06

*B

-0.06

peare

-0.06

POSITIVE LOGITS

》↵

0.06

.Gen

0.06

 заним

0.06

 deepcopy

0.06

 وصلات

0.06

のだ

0.06

 durum

0.06

__(

0.06

厂

0.06

']]

0.06

Activations Density 0.011%

image processing settings

The neuron activates on numeric configuration values (particularly floating‐point numbers) in the serialized texture settings.

No Comments

No Known Activations