INDEX

Explanations

references to bugs or issues in software development

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

-0.16

erchant

-0.14

UTERS

-0.14

_attrib

-0.14

Ã³ng

-0.14

LETTE

-0.14

wz

-0.13

ogan

-0.13

 coppia

-0.13

quot

-0.13

POSITIVE LOGITS

eu

0.28

pra

0.26

 tÃ´

0.23

pra

0.22

Eu

0.22

sei

0.21

acho

0.20

sou

0.20

vou

0.20

eu

0.19

Activations Density 0.030%

references to bugs or issues in software development

No Comments

No Known Activations