INDEX

Explanations

references to roles and positions in organizations or groups

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

 Contractor

-0.20

 Attorney

-0.17

 Producer

-0.17

 Prosecutor

-0.17

 Advisor

-0.16

 Coach

-0.16

 Committees

-0.16

 Defendant

-0.16

 Presenter

-0.15

 Commissioners

-0.15

POSITIVE LOGITS

 director

0.30

 vice

0.30

 executive

0.28

 deputy

0.27

 assistant

0.27

 chief

0.27

 president

0.26

 associate

0.26

 chairman

0.25

 communications

0.24

Activations Density 0.248%

references to roles and positions in organizations or groups

No Comments

No Known Activations