INDEX

Explanations

terms related to protective gear and materials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 Guns

-0.17

ç«

-0.15

guns

-0.15

gne

-0.14

 haired

-0.14

yan

-0.14

veis

-0.14

illa

-0.14

pth

-0.13

GAN

-0.13

POSITIVE LOGITS

 protection

0.29

 protective

0.26

 Protection

0.24

 protect

0.23

 Protective

0.22

 armor

0.21

 protects

0.21

Protection

0.21

protect

0.20

 layer

0.20

Activations Density 0.070%

terms related to protective gear and materials

No Comments

No Known Activations