INDEX

Explanations

positive and negative signs

np_max-act · gemini-2.0-flash

The neuron activates on signed numerical measurements (numbers preceded by ‘+’ or ‘–’).

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

Negative Logits

 inventive

-0.07

 ingen

-0.07

 chain

-0.06

 heavily

-0.06

_font

-0.06

uni

-0.06

 Eventually

-0.06

.overflow

-0.06

(cc

-0.06

Major

-0.06

POSITIVE LOGITS

)+↵

0.07

�

0.07

^.

0.06

––

0.06

 ноября

0.06

oč

0.06

บาย

0.06

 aday

0.06

(\$

0.06

\V

0.06

Activations Density 0.008%

positive and negative signs

The neuron activates on signed numerical measurements (numbers preceded by ‘+’ or ‘–’).

No Known Activations