INDEX

Explanations

concepts related to analysis and evaluation of outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 somehow

-0.20

orna

-0.17

ĨĴ

-0.16

ajas

-0.16

aml

-0.15

isay

-0.15

sÃŃ

-0.14

 anytime

-0.14

arger

-0.14

odox

-0.14

POSITIVE LOGITS

/how

0.38

 versus

0.31

 ÙĪÙħØ§

0.30

vs

0.30

 exactly

0.29

 besides

0.27

/if

0.27

ï¼Įä»¥åıĬ

0.27

 differently

0.26

ä»¥åıĬ

0.25

Activations Density 0.473%

concepts related to analysis and evaluation of outcomes

No Comments

No Known Activations