INDEX

Explanations

computer programs and scripts

np_max-act · gemini-2.0-flash

The neuron activates on references to the software system under discussion—words naming the program or service (e.g. “service,” “program,” “job,” or specific application names).

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

ट

-0.07

example

-0.07

 Rahul

-0.06

bal

-0.06

.study

-0.06

 blown

-0.06

sword

-0.06

 organize

-0.06

 traders

-0.06

.getResult

-0.06

POSITIVE LOGITS

 intrusive

0.07

omnia

0.06

 royalties

0.06

Equip

0.06

_NV

0.06

 Nicolas

0.06

(cuda

0.06

.Children

0.06

､

0.06

 Cyprus

0.06

Activations Density 0.135%

computer programs and scripts

The neuron activates on references to the software system under discussion—words naming the program or service (e.g. “service,” “program,” “job,” or specific application names).

No Comments

No Known Activations

computer programs and scripts

The neuron activates on references to the software system under discussion—words naming the program or service (e.g. “service,” “program,” “job,” or specific application names).

No Comments

No Known Activations