INDEX

Explanations

terms and concepts related to advanced mathematical structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Ã¼le

-0.16

Macro

-0.14

OTES

-0.14

eldon

-0.14

Ã¼f

-0.14

ejs

-0.14

ÑĥÐ¹

-0.13

ÑĥÐ½Ðº

-0.13

 Sloan

-0.13

 Tmax

-0.13

POSITIVE LOGITS

Lie

0.38

nil

0.30

Lie

0.29

-nil

0.27

 associative

0.27

lie

0.26

al

0.25

nil

0.24

 envelop

0.23

fil

0.22

Activations Density 0.018%

terms and concepts related to advanced mathematical structures

No Comments

No Known Activations