INDEX

Explanations

rankings and positions in competitions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ãĥ³ãĥĲ

-0.15

encing

-0.14

atto

-0.14

enga

-0.13

 samt

-0.13

Î´Î®

-0.13

.ie

-0.13

 nÄĽho

-0.13

baugh

-0.13

andin

-0.13

POSITIVE LOGITS

 place

0.38

 overall

0.36

overall

0.32

 Overall

0.31

place

0.31

Overall

0.28

 Ð¼ÐµÑģÑĤÐ¾

0.28

-place

0.27

 position

0.27

 Place

0.26

Activations Density 0.041%

rankings and positions in competitions or events

No Comments

No Known Activations