INDEX

Explanations

technical text

np_max-act · gemini-2.0-flash

This neuron detects numeric tokens (digits or numbers) in the text.

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

 awful

-0.07

wit

-0.06

 devast

-0.06

Ort

-0.06

combined

-0.06

 invo

-0.06

 opens

-0.06

 Resume

-0.06

 Websites

-0.06

POSITIVE LOGITS

 التعليم

0.07

PE

0.07

كر

0.07

ZY

0.07

_cpus

0.06

zman

0.06

│

0.06

addItem

0.06

든

0.06

本

0.06

Activations Density 0.000%

technical text

This neuron detects numeric tokens (digits or numbers) in the text.

No Comments

No Known Activations