INDEX

Explanations

references to legal matters and conflicts

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

esda

-0.14

lon

-0.14

ritch

-0.14

esel

-0.13

etc

-0.13

oub

-0.13

ico

-0.13

ç¯Ħ

-0.13

ä¼¦

-0.13

elsen

-0.13

POSITIVE LOGITS

one

0.42

åĪĨåĪ«

0.32

—one

0.29

-one

0.27

 ones

0.27

one

0.26

 satu

0.25

 ÛĮÚ©ÛĮ

0.25

 biri

0.25

 birinin

0.24

Activations Density 0.216%

references to legal matters and conflicts

No Comments

No Known Activations