INDEX

Explanations

geographical references and county names within specific locations, especially in North Dakota

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Mass

-0.26

Mass

-0.24

 mass

-0.21

Pa

-0.21

 masses

-0.20

mass

-0.20

 MASS

-0.19

pa

-0.19

MA

-0.19

Pa

-0.18

POSITIVE LOGITS

 Montana

0.28

 Wyoming

0.27

Wy

0.26

Neb

0.25

Wy

0.24

 Nebraska

0.23

MT

0.22

SD

0.22

 Idaho

0.22

KS

0.21

Activations Density 0.122%

geographical references and county names within specific locations, especially in North Dakota

No Comments

No Known Activations