INDEX

Explanations

specific measurements and dimensions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

pone

-0.15

itten

-0.14

etting

-0.14

ãĥ¼ãĥį

-0.13

udev

-0.13

ulos

-0.13

Iso

-0.13

æŃ¢

-0.12

 Helmet

-0.12

æĭ©

-0.12

POSITIVE LOGITS

 inch

0.41

 inches

0.40

-inch

0.40

inch

0.35

 Inch

0.34

-In

0.33

 Inches

0.33

-in

0.29

 Ø§ÛĮÙĨÚĨ

0.28

ãĤ¤ãĥ³

0.27

Activations Density 0.066%

specific measurements and dimensions

No Comments

No Known Activations