INDEX

Explanations

concepts related to quality and performance in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ers

-0.21

able

-0.20

ings

-0.19

erman

-0.18

(s

-0.18

ableObject

-0.18

ation

-0.17

age

-0.16

åĳĺ

-0.16

ered

-0.16

POSITIVE LOGITS

 factor

0.29

 levels

0.28

 quotient

0.26

 level

0.24

 rating

0.23

 ratings

0.22

 index

0.22

 issues

0.21

 factors

0.21

-minded

0.21

Activations Density 0.351%

concepts related to quality and performance in various contexts

No Comments

No Known Activations