INDEX

Explanations

HTML attributes

np_max-act · gemini-2.0-flash

The neuron activates on the word “visible” used as an XML attribute name in UI or layout definitions.

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

/tools

-0.07

てる

-0.06

ergus

-0.06

�

-0.06

αλ

-0.06

irus

-0.06

Roe

-0.06

mov

-0.06

POSITIVE LOGITS

printing

0.07

+"]

0.07

ывается

0.07

 stren

0.07

 MagicMock

0.06

	screen

0.06

yna

0.06

}))

0.06

 PdfPCell

0.06

 acciones

0.06

Activations Density 0.003%

HTML attributes

The neuron activates on the word “visible” used as an XML attribute name in UI or layout definitions.

No Comments

No Known Activations

HTML attributes

The neuron activates on the word “visible” used as an XML attribute name in UI or layout definitions.

No Comments

No Known Activations