INDEX

Explanations

root

np_max-act · gemini-2.0-flash

The neuron detects boilerplate license‐header lines that mention the “root directory” (e.g. “LICENSE file in the root directory of this source tree”).

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

ियल

-0.06

 languages

-0.06

ioc

-0.06

iam

-0.06

 refurb

-0.06

 slope

-0.06

 prav

-0.06

 coffee

-0.06

今天

-0.06

 args

-0.06

POSITIVE LOGITS

_TESTS

0.07

_Category

0.07

 ThemeData

0.06

]));
↵

0.06

 premier

0.06

VH

0.06

χή

0.06

NASDAQ

0.06

ADER

0.06

κρα

0.06

Activations Density 0.001%

root

The neuron detects boilerplate license‐header lines that mention the “root directory” (e.g. “LICENSE file in the root directory of this source tree”).

No Comments

No Known Activations