INDEX

Explanations

and,

np_max-act · gemini-2.0-flash

The neuron primarily detects floating‐point numeric values (decimal numbers) in the text.

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

.println

-0.07

 Garland

-0.06

 swipe

-0.06

 текст

-0.06

(build

-0.06

Rud

-0.06

巴

-0.06

.undo

-0.06

_UTILS

-0.06

 ↵↵↵↵↵

-0.06

POSITIVE LOGITS

raith

0.07

riott

0.07

 expres

0.07

"=>"

0.07

oleon

0.06

":"

0.06

กระ

0.06

=<

0.06

 рыб

0.06

 domic

0.06

Activations Density 0.135%

and,

The neuron primarily detects floating‐point numeric values (decimal numbers) in the text.

No Comments

No Known Activations