INDEX

Explanations

²

np_max-act · gemini-2.0-flash

The neuron selectively activates on decimal numeric values (e.g. precise area or density conversions in parentheses).

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

 fading

-0.07

-mon

-0.07

 Smile

-0.07

_logic

-0.06

سمة

-0.06

Что

-0.06

—or

-0.06

 Champion

-0.06

 От

-0.06

 Racing

-0.06

POSITIVE LOGITS

(resultado

0.07

 createStore

0.06

 courier

0.06

 Generate

0.06

 Athletics

0.06

χή

0.06

 interface

0.06

 feminism

0.06

prevState

0.06

 initWithTitle

0.06

Activations Density 0.000%

²

The neuron selectively activates on decimal numeric values (e.g. precise area or density conversions in parentheses).

No Comments

No Known Activations