INDEX

Explanations

phrases related to statistical measures or indicators of risk and health concerns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

FRING

-0.17

lier

-0.15

edii

-0.15

oley

-0.14

 remainder

-0.14

ÏĦÎµÏħ

-0.14

-0.13

reak

-0.13

stell

-0.13

SSID

-0.13

POSITIVE LOGITS

æľĢ

0.42

 ê°Ģìŀ¥

0.39

 æľĢ

0.38

 à¤¸à¤¬à¤¸

0.33

 ÑģÐ°Ð¼ÑĭÐ¹

0.30

the

0.28

 ÑģÐ°Ð¼ÑĭÐ¼

0.27

naj

0.27

æľĢé«ĺ

0.27

 ÑģÐ°Ð¼Ð¾Ð¼

0.27

Activations Density 0.405%

phrases related to statistical measures or indicators of risk and health concerns

No Comments

No Known Activations