INDEX

Explanations

beginning snippets

np_max-act · gemini-2.0-flash

The neuron responds to the single-letter token “a,” i.e. the indefinite article “a.”

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

_VALID

-0.06

的

-0.06

۲۰۲

-0.06

 centr

-0.06

 copper

-0.06

ı

-0.06

.content

-0.06

 слід

-0.06

 يمكن

-0.06

 Centers

-0.06

POSITIVE LOGITS

marginLeft

0.07

::=

0.07

Fay

0.07

BUTTONDOWN

0.06

romosome

0.06

 puzz

0.06

 McKay

0.06

Crear

0.06

Hal

0.06

unya

0.06

Activations Density 0.150%

beginning snippets

The neuron responds to the single-letter token “a,” i.e. the indefinite article “a.”

No Comments

No Known Activations