INDEX

Explanations

geographic locations and addresses

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

essian

-0.15

CRS

-0.15

Ø§ÙĦØ¥ÙĨØ¬ÙĦÙĬØ²ÙĬØ©

-0.15

.TextAlignment

-0.15

 DropIndex

-0.14

amos

-0.14

Tex

-0.14

unda

-0.14

adu

-0.14

ossa

-0.14

POSITIVE LOGITS

Kew

0.27

 Michigan

0.25

 Mack

0.24

 Manit

0.23

Hur

0.22

Michigan

0.21

 Pere

0.20

 Traverse

0.20

 Superior

0.20

Alg

0.20

Activations Density 0.024%

geographic locations and addresses

No Comments

No Known Activations