INDEX

Explanations

scientific studies

np_max-act · gemini-2.0-flash

This neuron activates on abstract noun forms denoting biological processes or measurements (e.g. terms ending in –ion, –ity, –sis).

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

AsString

-0.06

_Send

-0.06

λι

-0.06

 crunch

-0.06

agara

-0.06

망

-0.06

 shiny

-0.06

лось

-0.05

 Lyme

-0.05

 ngừng

-0.05

POSITIVE LOGITS

 slips

0.07

การส

0.07

 verifica

0.07

 Localization

0.07

.getChildren

0.07

 Career

0.07

 документа

0.06

cin

0.06

 satisf

0.06

 Penalty

0.06

Activations Density 0.036%

scientific studies

This neuron activates on abstract noun forms denoting biological processes or measurements (e.g. terms ending in –ion, –ity, –sis).

No Comments

No Known Activations

scientific studies

This neuron activates on abstract noun forms denoting biological processes or measurements (e.g. terms ending in –ion, –ity, –sis).

No Comments

No Known Activations