INDEX

Explanations

>

np_max-act · gemini-2.0-flash

This neuron detects Markdown- or email-style blockquote markers (lines beginning with “>”).

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

א

-0.07

 Blues

-0.06

 worksheets

-0.06

_msg

-0.06

γμα

-0.06

 MainForm

-0.06

 Attempt

-0.06

.Reg

-0.06

(userData

-0.06

landscape

-0.06

POSITIVE LOGITS

ƒ

0.07

>s

0.06

ìm

0.06

//<

0.06

سي

0.06

ес

0.06

BOR

0.06

iedo

0.06

″E

0.06

ül

0.06

Activations Density 0.003%

>

This neuron detects Markdown- or email-style blockquote markers (lines beginning with “>”).

No Comments

No Known Activations