INDEX

Explanations

Hello

np_max-act · gemini-2.0-flash

This neuron responds to string literals in code examples—particularly the “Hello” and “World” tokens inside print statements (e.g. “print("Hello, World")”).

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

카

-0.07

У

-0.06

存于

-0.06

 فرآ

-0.06

ايد

-0.06

 elig

-0.06

 genital

-0.06

.or

-0.06

 BitConverter

-0.06

Ars

-0.06

POSITIVE LOGITS

期

0.06

opcion

0.06

 Kosovo

0.06

民

0.06

 Beet

0.06

retorno

0.06

σφα

0.06

 Lincoln

0.06

bcm

0.06

ean

0.06

Activations Density 0.012%

Hello

This neuron responds to string literals in code examples—particularly the “Hello” and “World” tokens inside print statements (e.g. “print("Hello, World")”).

No Comments

No Known Activations

Hello

This neuron responds to string literals in code examples—particularly the “Hello” and “World” tokens inside print statements (e.g. “print("Hello, World")”).

No Comments

No Known Activations