INDEX

Explanations

phrases indicating moral judgments or ethical considerations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ief

-0.16

åĮĸ

-0.14

_VERIFY

-0.14

elm

-0.14

.scalablytyped

-0.14

ney

-0.14

lever

-0.14

-0.13

 actionTypes

-0.13

Î»Ïī

-0.13

POSITIVE LOGITS

 others

0.18

xes

0.16

 vice

0.15

 weather

0.15

rottle

0.15

 likewise

0.15

 other

0.14

olis

0.14

 similarly

0.14

others

0.14

Activations Density 0.160%

phrases indicating moral judgments or ethical considerations

No Comments

No Known Activations