INDEX

Explanations

making

np_max-act · gemini-2.0-flash

The neuron is primarily firing on numeric price or cost expressions (e.g. dollar amounts).

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

 براى

-0.07

 saldırı

-0.07

VR

-0.06

aries

-0.06

cích

-0.06

こそ

-0.06

 traces

-0.06

 suspicions

-0.06

Administrator

-0.06

 dbus

-0.06

POSITIVE LOGITS

<Class

0.07

allele

0.06

 الأخ

0.06

Bracket

0.06

mac

0.06

_CN

0.06

/in

0.06

/auto

0.06

CGPoint

0.06

initely

0.06

Activations Density 0.124%

making

The neuron is primarily firing on numeric price or cost expressions (e.g. dollar amounts).

No Comments

No Known Activations

making

The neuron is primarily firing on numeric price or cost expressions (e.g. dollar amounts).

No Comments

No Known Activations