INDEX

Explanations

technology

np_max-act · gemini-2.0-flash

The neuron strongly activates on mentions of specific software platforms or their version identifiers (e.g. “WordPress,” “Drupal,” “2005”).

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

rance

-0.06

 codes

-0.06

-dropdown

-0.06

aga

-0.06

 earrings

-0.06

 sites

-0.06

erman

-0.06

ya

-0.06

figures

-0.06

ardon

-0.06

POSITIVE LOGITS

 Samsung

0.07

.problem

0.06

کز

0.06

tum

0.06

endphp

0.06

.signIn

0.06

_StaticFields

0.06

 tanı

0.06

oenix

0.06

	cerr

0.06

Activations Density 0.176%

technology

The neuron strongly activates on mentions of specific software platforms or their version identifiers (e.g. “WordPress,” “Drupal,” “2005”).

No Comments

No Known Activations