INDEX

Explanations

HTML characters

np_max-act · gemini-2.0-flash

This neuron fires on HTML markup tags (i.e. angle-bracketed `<…>` elements).

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

Preferences

-0.07

 хочу

-0.07

wow

-0.07

enting

-0.06

iyan

-0.06

_Man

-0.06

.getTitle

-0.06

دان

-0.06

 shades

-0.06

 :-↵

-0.06

POSITIVE LOGITS

0.07

_GAIN

0.07

 FormsModule

0.07

_redirect

0.06

 reclaim

0.06

 एस

0.06

 unsettling

0.06

ائی

0.06

斗

0.06

xhr

0.06

Activations Density 0.004%

HTML characters

This neuron fires on HTML markup tags (i.e. angle-bracketed `<…>` elements).

No Comments

No Known Activations