INDEX

Explanations

instances of misconduct and formal investigations related to professional behavior

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ÐµÐ»Ðµ

-0.17

Prosec

-0.16

adian

-0.16

 Prosec

-0.16

 prosecuted

-0.16

.setViewport

-0.15

 Stateless

-0.15

/kernel

-0.15

 extradition

-0.15

 Watt

-0.15

POSITIVE LOGITS

 discipline

0.35

 discipl

0.34

 disciplinary

0.32

 Discipline

0.29

 internal

0.27

 Ð´Ð¸ÑģÑĨÐ¸Ð¿

0.26

 disciplines

0.25

 disciplined

0.24

 union

0.24

 Internal

0.23

Activations Density 0.062%

instances of misconduct and formal investigations related to professional behavior

No Comments

No Known Activations