INDEX

Explanations

all

np_max-act · gemini-2.0-flash

The neuron specifically responds to the verb “immerse” (and words of that same stem), flagging instances of “immerse” (deep involvement) in the text.

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

str

-0.07

quivo

-0.06

 рост

-0.06

Segoe

-0.06

-sm

-0.06

 сигн

-0.06

 провести

-0.06

 Drug

-0.06

 kadınlar

-0.06

POSITIVE LOGITS

 Nhất

0.07

all

0.07

ICollectionView

0.07

LOT

0.07

/max

0.06

atility

0.06

 scaled

0.06

lash

0.06

��

0.06

ially

0.06

Activations Density 0.028%

all

The neuron specifically responds to the verb “immerse” (and words of that same stem), flagging instances of “immerse” (deep involvement) in the text.

No Comments

No Known Activations