INDEX

Explanations

references to sports team updates and player conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

abwe

-0.16

Mal

-0.15

 Malaysia

-0.15

rix

-0.15

MAL

-0.15

 ÙħØ§ÙĦ

-0.14

MAL

-0.14

mal

-0.14

 Royale

-0.14

 Everton

-0.14

POSITIVE LOGITS

 Mets

0.38

Met

0.32

MET

0.28

 Queens

0.27

Met

0.26

NY

0.26

NY

0.26

/met

0.26

 Brooklyn

0.25

omet

0.25

Activations Density 0.043%

references to sports team updates and player conditions

No Comments

No Known Activations