INDEX

Explanations

phrases related to roles and locations within community and organizational contexts

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

 Lone

-0.15

ceae

-0.15

Fab

-0.15

å¨ľ

-0.15

olson

-0.15

oling

-0.15

Fab

-0.14

 Pacific

-0.14

 barg

-0.14

 Traverse

-0.14

POSITIVE LOGITS

 Hampshire

0.35

 Berkshire

0.34

 Lanc

0.32

 Worce

0.32

 Essex

0.32

 Surrey

0.31

 Kent

0.31

Dor

0.30

 Buckingham

0.29

 Beds

0.28

Activations Density 0.119%

phrases related to roles and locations within community and organizational contexts

No Comments

No Known Activations