INDEX

Explanations

references to historical or cultural relationships between nations and minority groups

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

bedo

-0.14

 countries

-0.14

ecessarily

-0.14

egas

-0.14

 Americans

-0.14

orado

-0.13

Å¡ÃŃ

-0.13

 bald

-0.13

 Bald

-0.13

icap

-0.13

POSITIVE LOGITS

 minority

0.35

 minorities

0.31

 Minority

0.29

minor

0.25

 Minor

0.25

Minor

0.24

eth

0.22

 ethnic

0.21

 thiá»ĥu

0.21

 numer

0.21

Activations Density 0.095%

references to historical or cultural relationships between nations and minority groups

No Known Activations