INDEX

Explanations

<

np_max-act · gemini-2.0-flash

The neuron detects HTML/XML markup elements, i.e. text enclosed in angle-bracket tags.

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

uplicates

-0.08

ocre

-0.07

ื

-0.07

 bursting

-0.07

ุบ

-0.06

iants

-0.06

client

-0.06

íně

-0.06

igenous

-0.06

reate

-0.06

POSITIVE LOGITS

 Straw

0.08

_basic

0.06

[DllImport

0.06

 Elasticsearch

0.06

 Abdel

0.06

 FileNotFoundException

0.06

@protocol

0.06

 approximation

0.06

 studs

0.06

Vous

0.06

Activations Density 0.020%

<

The neuron detects HTML/XML markup elements, i.e. text enclosed in angle-bracket tags.

No Comments

No Known Activations