INDEX

Explanations

references to construction, facilities, and various types of buildings and their attributes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ucht

-0.15

fte

-0.15

 Interior

-0.15

Interior

-0.14

 Door

-0.14

ips

-0.14

è¡Ĺéģĵ

-0.14

ÑĢÑĥÑĤ

-0.14

anel

-0.14

 Canal

-0.14

POSITIVE LOGITS

 office

0.28

 offices

0.27

 kitchen

0.26

 library

0.25

office

0.22

gym

0.22

åĬŀåħ¬

0.21

 showers

0.21

 Offices

0.19

 classroom

0.19

Activations Density 0.182%

references to construction, facilities, and various types of buildings and their attributes

No Comments

No Known Activations