INDEX

Explanations

change

np_max-act · gemini-2.0-flash

The neuron activates on occurrences of the substring “change” (as in identifiers or package/module names containing “xchange”).

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

["$

-0.07

Ї

-0.07

Zend

-0.06

Seat

-0.06

 twig

-0.06

.MODEL

-0.06

 atlas

-0.06

 člově

-0.06

 výsled

-0.06

=key

-0.06

POSITIVE LOGITS

 departamento

0.06

 practiced

0.06

ys

0.06

 Named

0.06

cum

0.06

 fossil

0.06

_TIME

0.06

 impressed

0.06

 nations

0.06

Activations Density 0.000%

change

The neuron activates on occurrences of the substring “change” (as in identifiers or package/module names containing “xchange”).

No Comments

No Known Activations