INDEX

Explanations

specific elements related to data management and classification

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

 Williamson

-0.30

 Buchanan

-0.23

 Hanson

-0.23

 Lucia

-0.23

arius

-0.21

 Jeremiah

-0.20

 Coleman

-0.20

 Clarkson

-0.19

 Bowman

-0.19

 Carlton

-0.19

POSITIVE LOGITS

 Karen

0.28

Karen

0.25

 Payne

0.23

ahren

0.21

 Lauren

0.21

Yao

0.20

 Airbnb

0.20

 Flynn

0.19

Activations Density 0.306%

specific elements related to data management and classification

No Comments

No Known Activations