INDEX

Explanations

technical terms and phrases related to engineering and performance metrics

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

oga

-0.18

rete

-0.15

åĦ

-0.15

kla

-0.15

tempt

-0.14

 âĹĦ

-0.14

 bounty

-0.14

rosso

-0.14

_hook

-0.13

 Landscape

-0.13

POSITIVE LOGITS

 lubric

0.42

Lub

0.37

 trib

0.35

lub

0.34

lub

0.32

 Trib

0.29

æ¶¦

0.28

 journal

0.28

 grease

0.28

 wear

0.27

Activations Density 0.045%

technical terms and phrases related to engineering and performance metrics

No Comments

No Known Activations