INDEX

Explanations

references to websites, technical issues, and troubleshooting scenarios

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

ÙĪÙĦÙĬ

-0.16

Úĺ

-0.15

ivos

-0.14

PDF

-0.14

uttle

-0.13

è±ª

-0.13

ÃŃÅ¡

-0.13

scalar

-0.13

VIR

-0.13

Ã¡Å¡

-0.13

POSITIVE LOGITS

 Stack

0.43

SE

0.36

 stack

0.36

Stack

0.34

.SE

0.32

.stack

0.31

.Stack

0.30

SO

0.30

 Meta

0.29

 meta

0.29

Activations Density 0.019%

references to websites, technical issues, and troubleshooting scenarios

No Comments

No Known Activations