INDEX

Explanations

references to travel and tourism activities

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

wang

-0.18

 Yosemite

-0.17

Oregon

-0.16

à¸£à¸£

-0.16

.onViewCreated

-0.15

 Albuquerque

-0.15

 Yosh

-0.15

 Tacoma

-0.15

 Oregon

-0.15

 Aless

-0.14

POSITIVE LOGITS

 Barb

0.50

 Caribbean

0.50

 Trinidad

0.48

 Jamaica

0.47

 Jama

0.46

 island

0.41

 Gren

0.40

 Bahamas

0.40

Guy

0.39

Cay

0.36

Activations Density 0.239%

references to travel and tourism activities

No Comments

No Known Activations