INDEX

Explanations

references to racism and social justice issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

odka

-0.15

leh

-0.14

 Retrie

-0.14

winter

-0.13

aniu

-0.13

vvm

-0.13

alem

-0.13

 winters

-0.13

èĪĮ

-0.13

claimer

-0.13

POSITIVE LOGITS

 Floyd

0.38

 George

0.37

 Minneapolis

0.33

George

0.32

 Derek

0.26

 protests

0.25

 police

0.23

 kneeling

0.22

 officers

0.22

 officer

0.22

Activations Density 0.044%

references to racism and social justice issues

No Comments

No Known Activations