INDEX

Explanations

includes

np_max-act · gemini-2.0-flash

This neuron recognizes formal patent‐claim language, especially method steps introduced by “comprising.”

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

SE

-0.07

No

-0.06

their

-0.06

AF

-0.06

ZIP

-0.06

 INIT

-0.06

(br

-0.06

(Resources

-0.06

Justice

-0.06

งของ

-0.06

POSITIVE LOGITS

 anecd

0.07

产业

0.07

orThunk

0.06

�

0.06

coi

0.06

ได

0.06

ؤول

0.06

rfl

0.06

_utf

0.06

 ساخته

0.06

Activations Density 0.007%

includes

This neuron recognizes formal patent‐claim language, especially method steps introduced by “comprising.”

No Comments

No Known Activations