INDEX

Explanations

examples and questions

np_max-act · gemini-2.0-flash

This neuron activates on special control/formatting tokens (e.g. header or end-of-text markers) rather than on actual content.

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

apan

-0.07

.googleapis

-0.07

 Extr

-0.07

/moment

-0.07

='<

-0.06

-mean

-0.06

Evo

-0.06

湿

-0.06

;?>

-0.06

uxt

-0.06

POSITIVE LOGITS

 Mundo

0.07

 frac

0.07

_DEPRECATED

0.07

*width

0.07

"label

0.06

////////

0.06

 strives

0.06

."/

0.06

 MIDI

0.06

burgh

0.06

Activations Density 0.061%

examples and questions

This neuron activates on special control/formatting tokens (e.g. header or end-of-text markers) rather than on actual content.

No Comments

No Known Activations