INDEX

Explanations

references to various kinds of information and its importance or accuracy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Î»Î¹Î±

-0.14

INCREMENT

-0.14

ilet

-0.14

åı·

-0.14

èĻŁ

-0.14

 ëª¨ìĬµ

-0.13

glob

-0.13

alan

-0.13

Ã¹

-0.13

 âĹĦ

-0.13

POSITIVE LOGITS

 information

0.26

/info

0.23

 gathered

0.22

-information

0.21

 info

0.20

 available

0.20

ä¿¡æģ¯

0.20

 gathering

0.20

 Information

0.19

information

0.19

Activations Density 0.161%

references to various kinds of information and its importance or accuracy

No Comments

No Known Activations