INDEX

Explanations

references to social issues and structures related to oppression and inequality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

NCY

-0.15

inger

-0.15

ADATA

-0.15

 instead

-0.15

idas

-0.15

vla

-0.15

utschein

-0.14

á»Ľt

-0.14

jde

-0.14

utral

-0.14

POSITIVE LOGITS

 overt

0.26

 physical

0.25

 obvious

0.23

physical

0.23

 Physical

0.23

Physical

0.20

 ÙħØ¨Ø§Ø´

0.20

 direct

0.20

direct

0.18

 directly

0.18

Activations Density 0.291%

references to social issues and structures related to oppression and inequality

No Comments

No Known Activations