INDEX

Explanations

technical programming details and syntax

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

 Second

-0.34

 second

-0.33

 SECOND

-0.31

 Ø§ÙĦØ«Ø§ÙĨÙĬ

-0.30

ç¬¬äºĮ

-0.30

äºĮ

-0.29

zwe

-0.29

second

-0.28

 segunda

-0.28

 Secondly

-0.28

POSITIVE LOGITS

0.27

0.23

0.22

0.18

('../../../

0.16

âĳ

0.15

 third

0.15

onus

0.15

0.14

Activations Density 0.088%

technical programming details and syntax

No Comments

No Known Activations