INDEX

Explanations

technical language related to statistical modeling and regression analysis

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

doz

-0.15

rel

-0.14

 Gros

-0.14

Rel

-0.13

=ax

-0.13

ÏĥÏĦÎµ

-0.13

lou

-0.13

Traversal

-0.13

 ÑĢÐ°Ð¹

-0.12

(rel

-0.12

POSITIVE LOGITS

aut

0.36

Aut

0.32

 autoc

0.30

 station

0.30

AR

0.28

 ARCH

0.28

 auto

0.27

 Station

0.27

-aut

0.27

lag

0.26

Activations Density 0.020%

technical language related to statistical modeling and regression analysis

No Comments

No Known Activations