INDEX

Explanations

references to countries and international programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Europe

-0.20

 europe

-0.19

 Scandin

-0.18

 Spanish

-0.18

 Asians

-0.18

 european

-0.18

 Europeans

-0.18

Spanish

-0.17

 italian

-0.17

Europe

-0.17

POSITIVE LOGITS

 Burk

0.34

 Chad

0.33

Guy

0.33

 Sierra

0.32

Sen

0.30

Bur

0.29

Moz

0.28

Guy

0.28

Gab

0.27

 Ivory

0.27

Activations Density 0.315%

references to countries and international programs

No Comments

No Known Activations