INDEX

Explanations

legal documents

np_max-act · gemini-2.0-flash

The neuron selectively activates on numeric tokens used as volume or page numbers in legal case citations.

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

 Rück

-0.07

 Master

-0.07

Master

-0.06

capture

-0.06

 هنر

-0.06

 хочу

-0.06

ама

-0.06

地下

-0.06

 prizes

-0.06

/auto

-0.06

POSITIVE LOGITS

sim

0.08

 aforementioned

0.06

fullName

0.06

 Пом

0.06

 personalized

0.06

emek

0.06

้อม

0.06

 concession

0.06

Tue

0.06

(Code

0.06

Activations Density 0.014%

legal documents

The neuron selectively activates on numeric tokens used as volume or page numbers in legal case citations.

No Comments

No Known Activations