INDEX

Explanations

title

np_max-act · gemini-2.0-flash

code-related questions or issues within a programming context.

oai_token-act-pair · gpt-4o-mini Triggered by @xinyanhu8

The neuron flags instances of the word “title” in code or JSON contexts.

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

.USER

-0.07

 Cutting

-0.07

(header

-0.06

�

-0.06

int

-0.06

World

-0.06

िकत

-0.06

.К

-0.06

/'↵↵

-0.06

мов

-0.06

POSITIVE LOGITS

ça

0.07

ฮ

0.07

 retain

0.07

.Ordinal

0.07

 ausge

0.06

 Locate

0.06

-guard

0.06

pau

0.06

=length

0.06

 Recreation

0.06

Activations Density 0.022%

title

code-related questions or issues within a programming context.

The neuron flags instances of the word “title” in code or JSON contexts.

No Comments

No Known Activations