INDEX

Explanations

correct

np_max-act · gemini-2.0-flash

The neuron never fires—it doesn’t detect any token and appears to be effectively “dead.”

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

 نیست

-0.06

scroll

-0.06

slideUp

-0.06

redicate

-0.06

樂

-0.06

lace

-0.06

 میکن

-0.06

notation

-0.06

 seper

-0.06

 hardest

-0.06

POSITIVE LOGITS

 Куб

0.07

 persisted

0.06

inya

0.06

 deney

0.06

noinspection

0.06

fla

0.06

 Вони

0.06

DATED

0.06

_cat

0.06

 Momentum

0.05

Activations Density 0.016%

correct

The neuron never fires—it doesn’t detect any token and appears to be effectively “dead.”

No Comments

No Known Activations