INDEX

Explanations

start

np_max-act · gemini-2.0-flash

The neuron activates on the metadata header lines in SysV/LSB init scripts (e.g. “Required-Start:”, “Default-Stop:”, “Provides:”, etc.).

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

 misma

-0.07

GUI

-0.06

 Release

-0.06

 prepend

-0.06

 Rune

-0.06

 Adelaide

-0.06

"B

-0.06

 intensity

-0.06

?(:

-0.06

랑

-0.06

POSITIVE LOGITS

i�

0.07

 сост

0.07

 Campaign

0.06

 Claim

0.06

getStatusCode

0.06

UM

0.06

�

0.06

 Laravel

0.06

 BOOLEAN

0.06

.Mongo

0.06

Activations Density 0.010%

start

The neuron activates on the metadata header lines in SysV/LSB init scripts (e.g. “Required-Start:”, “Default-Stop:”, “Provides:”, etc.).

No Comments

No Known Activations