INDEX

Explanations

Extracted/Scraped text

np_max-act · gemini-2.0-flash

This neuron detects HTML-style character entities (like “’”, “‘”, “’”, etc.).

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

>v

-0.07

+v

-0.07

ex

-0.07

=b

-0.06

μαν

-0.06

.option

-0.06

桐

-0.06

(v

-0.06

hat

-0.06

-wing

-0.06

POSITIVE LOGITS

 ListBox

0.07

Ellipse

0.07

IBUTES

0.07

addEventListener

0.06

getElement

0.06

 cage

0.06

achten

0.06

 DISTINCT

0.06

CharArray

0.06

trajectory

0.06

Activations Density 0.006%

Extracted/Scraped text

This neuron detects HTML-style character entities (like “&#8217;”, “&lsquo;”, “&rsquo;”, etc.).

No Comments

No Known Activations

This neuron detects HTML-style character entities (like “’”, “‘”, “’”, etc.).