INDEX

Explanations

3

np_max-act · gemini-2.0-flash

The neuron activates on standalone numeric tokens—especially the “3” version numbers in HTML/XML DOCTYPE declarations.

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

ieg

-0.07

-0.06

�

-0.06

 эта

-0.06

`t

-0.06

ESSAGE

-0.06

 nữ

-0.06

 shutter

-0.06

POSITIVE LOGITS

_Channel

0.08

 Arrow

0.07

 hardships

0.07

eventType

0.07

秀

0.06

 wife

0.06

 обличчя

0.06

 Lilly

0.06

 mama

0.06

 medicinal

0.06

Activations Density 0.000%

3

The neuron activates on standalone numeric tokens—especially the “3” version numbers in HTML/XML DOCTYPE declarations.

No Comments

No Known Activations