INDEX

Explanations

indicators of notable entities or significant qualities related to professional backgrounds or achievements

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

Nha

-0.14

AccessType

-0.14

 Texans

-0.14

Philadelphia

-0.13

 Michigan

-0.13

FDA

-0.13

 Delegate

-0.13

 Bronx

-0.13

otron

-0.13

 Berkshire

-0.13

POSITIVE LOGITS

 Euros

0.26

 euros

0.24

 centre

0.23

 parties

0.22

 euro

0.21

 Greece

0.20

 left

0.20

SPD

0.19

 Merkel

0.19

 Euro

0.19

Activations Density 0.007%

indicators of notable entities or significant qualities related to professional backgrounds or achievements

No Comments

No Known Activations