INDEX

Explanations

German nouns and descriptors indicating nationality or profession

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Äįi

-0.17

emens

-0.16

celik

-0.15

ureau

-0.15

addock

-0.15

CreateInfo

-0.14

enen

-0.14

 Peygamber

-0.14

incess

-0.14

andro

-0.14

POSITIVE LOGITS

 Journal

0.27

 Polit

0.25

 Autor

0.24

Jur

0.24

 Illustrator

0.23

Mal

0.22

 Dipl

0.21

 Manager

0.21

 Ingen

0.21

 Professor

0.21

Activations Density 0.021%

German nouns and descriptors indicating nationality or profession

No Comments

No Known Activations