INDEX

Explanations

err

np_max-act · gemini-2.0-flash

This neuron detects floating‐point numeric literals (tokens containing decimal points) in code.

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

 Pluto

-0.06

 пласти

-0.06

英语

-0.06

 REMOVE

-0.06

_serialize

-0.06

_follow

-0.06

ất

-0.06

-btn

-0.06

uyện

-0.06

 фактор

-0.06

POSITIVE LOGITS

 forums

0.06

lon

0.06

 Harding

0.06

 Δι

0.06

 numRows

0.06

 Worm

0.06

 Rocket

0.06

 Viet

0.06

Activations Density 0.002%

err

This neuron detects floating‐point numeric literals (tokens containing decimal points) in code.

No Comments

No Known Activations