INDEX

Explanations

/

np_max-act · gemini-2.0-flash

The neuron detects parts of programming-style path or package names (e.g. directory segments in URLs).

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

.Board

-0.06

لمات

-0.06

(sock

-0.06

無し�

-0.06

:@""

-0.06

 شیر

-0.06

+'&

-0.06

ičky

-0.06

_erase

-0.06

/mock

-0.06

POSITIVE LOGITS

>");
↵

0.07

est

0.07

 lãi

0.07

 gruesome

0.06

PasswordEncoder

0.06

感情

0.06

 medically

0.06

VENTORY

0.06

 Υπο

0.06

mtime

0.06

Activations Density 0.000%

/

The neuron detects parts of programming-style path or package names (e.g. directory segments in URLs).

No Comments

No Known Activations