INDEX

Explanations

@

np_max-act · gemini-2.0-flash

The neuron activates on Javadoc-style annotation tags (e.g. the “@param”, “@return”, etc. markers).

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

 Sentry

-0.07

-0.06

 ')↵

-0.06

ServiceProvider

-0.06

 worship

-0.06

dry

-0.06

 Matter

-0.06

 excl

-0.06

ผ

-0.06

POSITIVE LOGITS

_bs

0.07

刘

0.06

 παι

0.06

 valign

0.06

 spel

0.06

_ev

0.06

iefs

0.06

uple

0.06

apore

0.06

mekte

0.06

Activations Density 0.006%

@

The neuron activates on Javadoc-style annotation tags (e.g. the “@param”, “@return”, etc. markers).

No Comments

No Known Activations