INDEX

Explanations

BuilderFactory

np_max-act · gemini-2.0-flash

The neuron activates on names of Java XML‐processing API classes and factories (e.g., DocumentBuilderFactory, TransformerFactory, ParserConfigurationException).

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

del

-0.06

IE

-0.06

amarin

-0.06

 resorts

-0.06

，她

-0.06

 Swarm

-0.06

Verts

-0.06

 Sutton

-0.06

 Trump

-0.06

 smlouvy

-0.06

POSITIVE LOGITS

 снова

0.07

 چند

0.07

 خدا

0.07

 chiến

0.07

 amphib

0.07

 piyas

0.06

 periodically

0.06

 عشر

0.06

이크

0.06

 Chiến

0.06

Activations Density 0.002%

BuilderFactory

The neuron activates on names of Java XML‐processing API classes and factories (e.g., DocumentBuilderFactory, TransformerFactory, ParserConfigurationException).

No Comments

No Known Activations