INDEX

Explanations

§

np_max-act · gemini-2.0-flash

The neuron detects legal citation tokens—numbers, section symbols, and abbreviations used in statute and case references.

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

 captivity

-0.06

.Invalid

-0.06

 wireless

-0.06

 cocktails

-0.06

(Book

-0.06

 naked

-0.06

 теат

-0.06

opencv

-0.06

Slider

-0.06

 rarely

-0.06

POSITIVE LOGITS

 hrom

0.07

อเม

0.07

çek

0.07

!↵

0.07

ployment

0.06

 مرکزی

0.06

 ديگر

0.06

 Measures

0.06

mip

0.06

 perí

0.06

Activations Density 0.003%

§

The neuron detects legal citation tokens—numbers, section symbols, and abbreviations used in statute and case references.

No Comments

No Known Activations