INDEX

Explanations

geographical locations and contexts related to work and residency

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ynchron

-0.16

 Scotia

-0.15

 Belize

-0.15

alia

-0.14

 Nicar

-0.14

Î½Î¿Ïħ

-0.14

 Chattanooga

-0.14

 Lanka

-0.14

atu

-0.14

aland

-0.13

POSITIVE LOGITS

 England

0.29

 London

0.27

Los

0.27

 Europe

0.26

 Germany

0.24

 California

0.24

 Texas

0.23

 Italy

0.23

New

0.22

 Paris

0.22

Activations Density 0.297%

geographical locations and contexts related to work and residency

No Comments

No Known Activations