INDEX

Explanations

references to racial or cultural topics, particularly those involving African American culture or notable figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

odore

-0.17

/email

-0.17

 eens

-0.16

pard

-0.16

URIComponent

-0.16

RD

-0.15

ãĥ³ãĥĸ

-0.15

ellas

-0.15

xima

-0.15

adera

-0.15

POSITIVE LOGITS

/disable

0.20

izabeth

0.19

 dÃłng

0.18

 coli

0.17

rics

0.17

-lfs

0.16

SCO

0.16

hardt

0.15

vironment

0.15

-disable

0.15

Activations Density 1.445%

references to racial or cultural topics, particularly those involving African American culture or notable figures

No Comments

No Known Activations