INDEX

Explanations

using

np_max-act · gemini-2.0-flash

This neuron activates on C# “using” statements that introduce a resource‐acquisition block.

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-b

-0.07

 їй

-0.07

Con

-0.06

!=

-0.06

hè

-0.06

 Server

-0.06

 safezone

-0.06

 impres

-0.06

Smart

-0.06

Nä

-0.06

POSITIVE LOGITS

-leaning

0.09

anitize

0.06

 Leicester

0.06

공부

0.06

imports

0.06

IMUM

0.06

 evenly

0.06

.getById

0.06

 číslo

0.06

ститут

0.06

Activations Density 0.001%

using

This neuron activates on C# “using” statements that introduce a resource‐acquisition block.

No Comments

No Known Activations

using

This neuron activates on C# “using” statements that introduce a resource‐acquisition block.

No Comments

No Known Activations