INDEX

Explanations

elements related to geographic locations and community activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 Canadians

-0.19

 Canada

-0.18

 Canadian

-0.18

Canada

-0.17

Canadian

-0.16

acen

-0.16

gob

-0.15

umlu

-0.15

 canada

-0.15

hai

-0.14

POSITIVE LOGITS

 Thunder

0.28

Abb

0.27

 Miss

0.27

Kam

0.27

Kel

0.27

 Bram

0.26

 Regina

0.26

 Hamilton

0.26

 Prince

0.26

 Medicine

0.25

Activations Density 0.265%

elements related to geographic locations and community activities

No Comments

No Known Activations