INDEX

Explanations

references to Australia and its contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

adow

-0.17

urtles

-0.15

Î²Î¬

-0.15

Ø´Ø§Ùĩ

-0.15

 Berkeley

-0.14

issippi

-0.14

à¤¾à¤²à¤ķ

-0.14

.JSON

-0.14

Ã¡du

-0.14

.Unicode

-0.14

POSITIVE LOGITS

 Australia

0.84

 Australian

0.82

 Australians

0.74

Australia

0.71

Australian

0.69

 Aussie

0.69

 Auss

0.65

AU

0.65

 australia

0.65

 Austral

0.64

Activations Density 0.285%

references to Australia and its contexts

No Comments

No Known Activations

references to Australia and its contexts

No Comments

No Known Activations