INDEX

Explanations

numerical data or measurements

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

ener

-0.18

ourse

-0.17

yc

-0.15

umber

-0.15

oner

-0.15

usic

-0.15

ÑĪÐºÐ°

-0.14

antan

-0.14

ken

-0.14

ourg

-0.14

POSITIVE LOGITS

ä»¥ä¸Ĭ

0.24

Above

0.21

 Above

0.21

+↵

0.20

 Beyond

0.19

AFX

0.18

 above

0.18

above

0.18

 ìĿ´ìĥģ

0.17

Beyond

0.17

Activations Density 0.005%

numerical data or measurements

No Comments

No Known Activations