INDEX

Explanations

proper nouns and names associated with individuals or teams

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

Åº

-0.15

 chalk

-0.15

æ©

-0.14

.appspot

-0.14

asu

-0.14

ÄŁ

-0.14

siz

-0.14

ults

-0.14

Äįet

-0.14

irsch

-0.14

POSITIVE LOGITS

 Walsh

0.26

 Daly

0.24

 Byrne

0.24

 Lynch

0.23

 Murphy

0.23

 Kelly

0.23

 McDon

0.22

Ã

0.22

 Ryan

0.22

0.21

Activations Density 0.095%

proper nouns and names associated with individuals or teams

No Comments

No Known Activations