INDEX

Explanations

server

np_max-act · gemini-2.0-flash

The neuron detects markup tag tokens (e.g. HTML/XML angle-bracket elements) 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

 Checkbox

-0.06

tron

-0.06

getRequest

-0.06

 عنوان

-0.06

_thr

-0.06

LTR

-0.06

 درس

-0.06

 refreshToken

-0.06

 tjejer

-0.06

 vědom

-0.06

POSITIVE LOGITS

 якого

0.06

RARY

0.06

 ascertain

0.06

 слыш

0.05

啪

0.05

 oracle

0.05

 toho

0.05

↵
↵
↵
↵

0.05

‌انبار

0.05

Activations Density 14.268%

server

The neuron detects markup tag tokens (e.g. HTML/XML angle-bracket elements) in the text.

No Comments

No Known Activations