INDEX

Explanations

Articles

np_max-act · gemini-2.0-flash

Explanation of neuron 4 behavior: the main thing this neuron does is find the indefinite articles “a” and “an.”

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

_constraint

-0.07

 consequently

-0.07

processor

-0.06

ESCO

-0.06

_cred

-0.06

 برگ

-0.06

 догов

-0.06

_VALID

-0.06

_Edit

-0.06

Errors

-0.06

POSITIVE LOGITS

\:

0.07

是什么

0.06

 nominees

0.06

centaje

0.06

,...↵↵

0.06

ूछ

0.06

永

0.06

 пой

0.06

   ↵↵

0.06

.unknown

0.06

Activations Density 0.037%

Articles

Explanation of neuron 4 behavior: the main thing this neuron does is find the indefinite articles “a” and “an.”

No Comments

No Known Activations