INDEX

Explanations

legal and liability-related terms and concepts

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

 hence

-0.17

/latest

-0.16

ÐºÐ°Ð²

-0.15

 thus

-0.14

ivid

-0.14

Ø³Ø§ÙĨ

-0.13

.usermodel

-0.13

à¸µà¸¢à¸ĩ

-0.13

à¸µà¸¢à¸Ķ

-0.13

 Åŀimdi

-0.13

POSITIVE LOGITS

 depending

0.28

 Depending

0.24

depending

0.23

 Again

0.21

Depending

0.21

æľīäºĽ

0.20

Again

0.19

 Talk

0.18

 Bear

0.18

 again

0.18

Activations Density 0.168%

legal and liability-related terms and concepts

No Comments

No Known Activations