INDEX

Explanations

references to organizational partnerships and licensing agreements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

od

-0.15

uben

-0.15

ph

-0.15

apt

-0.15

å¨

-0.14

zin

-0.14

APT

-0.14

overs

-0.14

Ø§Ø¨ÙĤ

-0.14

-0.13

POSITIVE LOGITS

 partner

0.29

 partners

0.26

 extern

0.25

 outs

0.23

 Partner

0.23

 external

0.23

partner

0.23

 External

0.21

external

0.21

Partner

0.20

Activations Density 0.287%

references to organizational partnerships and licensing agreements

No Comments

No Known Activations