INDEX

Explanations

will

np_max-act · gemini-2.0-flash

This neuron detects the standard GNU license disclaimer phrase—particularly the “it will be useful” wording in license boilerplate.

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

(Gravity

-0.06

 νε

-0.06

utc

-0.06

FACT

-0.06

_demo

-0.06

�

-0.06

 fakat

-0.05

τικός

-0.05

 weil

-0.05

 всі

-0.05

POSITIVE LOGITS

 jLabel

0.07

 export

0.07

wp

0.07

	QString

0.07

 Edition

0.07

 sporting

0.06

iplina

0.06

 constitu

0.06

	JButton

0.06

Activations Density 0.005%

will

This neuron detects the standard GNU license disclaimer phrase—particularly the “it will be useful” wording in license boilerplate.

No Comments

No Known Activations

will

This neuron detects the standard GNU license disclaimer phrase—particularly the “it will be useful” wording in license boilerplate.

No Comments

No Known Activations