INDEX

Explanations

.apache

np_max-act · gemini-2.0-flash

The neuron fires on Java package name prefixes in stack‐trace lines (e.g. “com.sun.enterprise” or “org.apache”).

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

 fertil

-0.07

 sens

-0.07

 fitte

-0.06

 Savior

-0.06

ZF

-0.06

Ｓ

-0.06

-shaped

-0.06

 Gardner

-0.06

 Matte

-0.06

 Blitz

-0.06

POSITIVE LOGITS

 civic

0.07

."'";↵

0.07

مع

0.07

.amazonaws

0.07

วล

0.06

 yıllık

0.06

iscrimination

0.06

.open

0.06

ार

0.06

 Hong

0.06

Activations Density 0.001%

.apache

The neuron fires on Java package name prefixes in stack‐trace lines (e.g. “com.sun.enterprise” or “org.apache”).

No Comments

No Known Activations