INDEX

Explanations

references to locations and specific names in the context of healthcare and legal situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 Seah

-0.21

à¹Ģà¸ģà¸¥

-0.16

nova

-0.16

 Oswald

-0.16

 Seattle

-0.15

rane

-0.15

 Tampa

-0.15

 Carnegie

-0.15

Ocean

-0.14

Seattle

-0.14

POSITIVE LOGITS

 Illinois

0.39

 Chicago

0.29

Chicago

0.27

 Nile

0.26

 Cubs

0.25

 chicago

0.24

 cytok

0.24

inois

0.23

 ÙħØµØ±

0.22

 Missouri

0.22

Activations Density 0.273%

references to locations and specific names in the context of healthcare and legal situations

No Comments

No Known Activations