INDEX

Explanations

numbers

np_max-act · gemini-2.0-flash

The neuron activates on numerical tokens, especially numbers and currency/quantity expressions.

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

 Vivo

-0.07

-pdf

-0.06

Fallback

-0.06

 fuzzy

-0.06

차

-0.06

 Skype

-0.06

 pragma

-0.06

 också

-0.06

-urlencoded

-0.06

.putString

-0.06

POSITIVE LOGITS

 aVar

0.07

Jessica

0.07

 aged

0.07

(CH

0.07

')");↵

0.07

！”↵↵

0.06

(GL

0.06

>}'

0.06

Because

0.06

}".

0.06

Activations Density 0.022%

numbers

The neuron activates on numerical tokens, especially numbers and currency/quantity expressions.

No Comments

No Known Activations