INDEX

Explanations

references to appointments or positions within judicial or government contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

rvine

-0.19

 Ontario

-0.16

 Cupertino

-0.16

Sri

-0.15

NH

-0.15

 Manitoba

-0.15

 Saskatchewan

-0.15

NSW

-0.14

 Lanka

-0.14

ContentLoaded

-0.14

POSITIVE LOGITS

 Mississippi

0.54

Miss

0.40

 Miss

0.35

 MISS

0.34

 Jackson

0.33

 miss

0.33

Tup

0.32

Ole

0.32

MS

0.32

Yaz

0.30

Activations Density 0.081%

references to appointments or positions within judicial or government contexts

No Comments

No Known Activations