INDEX

Explanations

*

np_max-act · gemini-2.0-flash

This neuron detects italicized or emphasized scientific names (markdown-style asterisks around species/genus terms).

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

HH

-0.07

 Мар

-0.07

Montserrat

-0.06

 descended

-0.06

 Publisher

-0.06

 macht

-0.06

 documentaries

-0.06

 investigators

-0.06

ンツ

-0.06

목

-0.06

POSITIVE LOGITS

\">"

0.07

>>::

0.07

)'

0.07

enderror

0.07

_lex

0.07

:'

0.07

》

0.06

(function

0.06

.out

0.06

ㆍ

0.06

Activations Density 0.008%

*

This neuron detects italicized or emphasized scientific names (markdown-style asterisks around species/genus terms).

No Comments

No Known Activations