INDEX

Explanations

specific geographic locations or addresses in a given context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 Farage

-0.14

adera

-0.14

lsruhe

-0.14

 Fiji

-0.14

UK

-0.14

 Australian

-0.14

uala

-0.14

 Australians

-0.13

 Europeans

-0.13

UK

-0.13

POSITIVE LOGITS

 QuÃ©bec

0.39

 Quebec

0.39

 Montreal

0.37

QuÃ©

0.33

 QuÃ©

0.32

Que

0.32

 quÃ©

0.31

QC

0.30

 McGill

0.29

Que

0.26

Activations Density 0.206%

specific geographic locations or addresses in a given context

No Comments

No Known Activations