INDEX

Explanations

references to specific racing teams and technical details related to Formula One cars

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

Nation

-0.15

 DÃ¼n

-0.15

Rail

-0.15

KUR

-0.15

antu

-0.14

 KÃ¼r

-0.14

-trained

-0.14

LAN

-0.14

 Ragnar

-0.14

ibus

-0.14

POSITIVE LOGITS

 Liberty

0.28

 Formula

0.25

 Bernie

0.24

Ecc

0.23

 sport

0.20

 Williams

0.19

 Force

0.19

 teams

0.19

 liberty

0.19

Activations Density 0.010%

references to specific racing teams and technical details related to Formula One cars

No Comments

No Known Activations