INDEX

Explanations

-

np_max-act · gemini-2.0-flash

The neuron activates on numeric patterns in regular expressions—specifically digit ranges (like `[0-9]`), numeric quantifiers (e.g. `{12}`), and related tokens.

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

 zřejmě

-0.08

 yapıldı

-0.07

 salaries

-0.06

 afternoon

-0.06

_heading

-0.06

.getDeclared

-0.06

 exposure

-0.06

POSITIVE LOGITS

 Прав

0.08

 öner

0.07

-how

0.07

 tailor

0.07

“你

0.06

-n

0.06

 Deutsch

0.06

 Investments

0.06

 asoci

0.06

 Initialise

0.06

Activations Density 0.001%

-

The neuron activates on numeric patterns in regular expressions—specifically digit ranges (like `[0-9]`), numeric quantifiers (e.g. `{12}`), and related tokens.

No Comments

No Known Activations