INDEX

Explanations

references to organizational roles and hierarchies

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

 Lomb

-0.15

ifr

-0.14

zym

-0.14

 Automobile

-0.14

 Motorcycle

-0.14

Motor

-0.14

 Garage

-0.14

 Monsanto

-0.13

 motorcycle

-0.13

pcb

-0.13

POSITIVE LOGITS

Kia

0.28

Rio

0.27

 trim

0.26

Rio

0.24

 hatch

0.23

rio

0.22

LX

0.21

trim

0.20

Hao

0.20

 Fiesta

0.20

Activations Density 0.003%

references to organizational roles and hierarchies

No Comments

No Known Activations