INDEX

Explanations

themes related to racial and social issues, particularly focusing on interracial couples and the challenges they face

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

.ManyToMany

-0.16

rets

-0.14

 Sentinel

-0.14

RootElement

-0.14

alaria

-0.14

Formatter

-0.14

alyze

-0.14

æŁ±

-0.14

çĮ®

-0.13

 fputs

-0.13

POSITIVE LOGITS

 discrimination

0.24

 treatment

0.19

 society

0.18

 harassment

0.17

 discriminatory

0.17

 Discrim

0.17

 doors

0.17

 discrim

0.17

 encounters

0.17

 discrimin

0.16

Activations Density 0.191%

themes related to racial and social issues, particularly focusing on interracial couples and the challenges they face

No Comments

No Known Activations