INDEX

Explanations

geographic directions and locations

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

 Southern

-0.20

 Northern

-0.18

alet

-0.16

riculum

-0.15

 Eastern

-0.15

uetype

-0.15

Southern

-0.15

klad

-0.15

stype

-0.14

 Western

-0.13

POSITIVE LOGITS

ward

0.49

wards

0.44

bound

0.41

-west

0.32

-east

0.31

 wards

0.28

-n

0.28

 ward

0.27

western

0.26

WARD

0.26

Activations Density 0.030%

geographic directions and locations

No Comments

No Known Activations