INDEX

Explanations

Abbreviations

np_max-act · gemini-2.0-flash

The neuron activates on short uppercase sequences (acronyms/initialisms), especially when they appear as parenthetical abbreviations.

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

clave

-0.07

 зап

-0.07

制度

-0.07

 constit

-0.07

يلم

-0.07

 menor

-0.06

ически

-0.06

 pool

-0.06

为

-0.06

POSITIVE LOGITS

Ï

0.06

.ResponseBody

0.06

Fortunately

0.06

cx

0.06

 чист

0.06

 -------↵

0.06

STATIC

0.06

ckså

0.06

 Redistributions

0.06

`"]↵

0.06

Activations Density 0.072%

Abbreviations

The neuron activates on short uppercase sequences (acronyms/initialisms), especially when they appear as parenthetical abbreviations.

No Comments

No Known Activations