INDEX

Explanations

code repositories

np_max-act · gemini-2.0-flash

The neuron selectively fires on the string tokens listed under the “keywords” array in these package-manifest JSON files.

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

ople

-0.07

[]{"

-0.06

มากกว

-0.06

 Мон

-0.06

 Achievement

-0.06

ça

-0.06

Cancellation

-0.06

	INNER

-0.06

roids

-0.06

 Magick

-0.06

POSITIVE LOGITS

添加

0.07

 Moreover

0.07

 forces

0.06

Moreover

0.06

کت

0.06

_den

0.06

 때문

0.06

 Fransız

0.06

 gamble

0.06

 último

0.06

Activations Density 0.003%

code repositories

The neuron selectively fires on the string tokens listed under the “keywords” array in these package-manifest JSON files.

No Comments

No Known Activations

code repositories

The neuron selectively fires on the string tokens listed under the “keywords” array in these package-manifest JSON files.

No Comments

No Known Activations