INDEX

Explanations

mentions of appointments and judicial positions

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

 Cupertino

-0.19

rvine

-0.18

 Calgary

-0.18

Toronto

-0.17

Australia

-0.17

 Lanka

-0.17

Canada

-0.17

Sri

-0.17

.vm

-0.17

 Vancouver

-0.16

POSITIVE LOGITS

 Mississippi

0.69

Miss

0.46

MS

0.42

 Miss

0.42

 MISS

0.41

Tup

0.39

 Jackson

0.37

 Gulf

0.36

Yaz

0.36

 miss

0.35

Activations Density 0.087%

mentions of appointments and judicial positions

No Comments

No Known Activations