INDEX

Explanations

moral evaluations and assessments of character

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

iliar

-0.16

Ã¼f

-0.16

ilder

-0.15

ointments

-0.14

 jadx

-0.14

_Static

-0.14

.lab

-0.14

acers

-0.14

.gdx

-0.14

ãĤ¿ãĤ¤

-0.14

POSITIVE LOGITS

 ethical

0.53

 moral

0.51

 ethics

0.48

 morality

0.45

 Moral

0.43

 Ethics

0.42

ethical

0.41

 morally

0.39

 morals

0.37

Eth

0.32

Activations Density 0.566%

moral evaluations and assessments of character

No Comments

No Known Activations

moral evaluations and assessments of character

No Comments

No Known Activations