INDEX

Explanations

ul

np_max-act · gemini-2.0-flash

The neuron strongly activates on the HTML closing unordered‐list tag (“</ul>”).

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FM

-0.07

 taraf

-0.07

Amp

-0.07

 Σχ

-0.06

-zone

-0.06

(counter

-0.06

levator

-0.06

 webs

-0.06

_coord

-0.06

军

-0.06

POSITIVE LOGITS

 artikel

0.07

 plunder

0.07

 topLevel

0.07

 віль

0.07

민

0.06

 uplifting

0.06

 літ

0.06

 Awakening

0.06

….

0.06

 plag

0.06

Activations Density 0.003%

ul

The neuron strongly activates on the HTML closing unordered‐list tag (“</ul>”).

No Comments

No Known Activations