INDEX

Explanations

protein families

np_max-act · gemini-2.0-flash

This neuron activates on phrases that specify membership in a biological or protein family.

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

.wh

-0.07

_der

-0.07

EN

-0.07

$info

-0.07

 |
↵

-0.06

 IDENT

-0.06

 lineHeight

-0.06

 SECRET

-0.06

 ----------------------------------------------------------------------↵

-0.06

 součástí

-0.06

POSITIVE LOGITS

Button

0.07

esco

0.06

іка

0.06

град

0.06

 Lola

0.06

bic

0.06

 Quad

0.06

 Double

0.06

 invoice

0.06

 küçük

0.06

Activations Density 0.016%

protein families

This neuron activates on phrases that specify membership in a biological or protein family.

No Comments

No Known Activations

protein families

This neuron activates on phrases that specify membership in a biological or protein family.

No Comments

No Known Activations