INDEX

Explanations

ITS

np_max-act · gemini-2.0-flash

The neuron fires on standalone title or heading text—short, prominently capitalized lines (e.g. section titles or article headers).

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

 introdu

-0.07

نام

-0.07

下载次数

-0.07

/alert

-0.06

]),↵

-0.06

 rehears

-0.06

 klik

-0.06

 lookout

-0.06

 complet

-0.06

 nailed

-0.06

POSITIVE LOGITS

 Arizona

0.07

 Outside

0.06

 powerless

0.06

execution

0.06

이션

0.06

$l

0.06

’a

0.06

','','

0.06

ole

0.06

 textual

0.06

Activations Density 0.066%

ITS

The neuron fires on standalone title or heading text—short, prominently capitalized lines (e.g. section titles or article headers).

No Comments

No Known Activations

ITS

The neuron fires on standalone title or heading text—short, prominently capitalized lines (e.g. section titles or article headers).

No Comments

No Known Activations