INDEX

Explanations

mentions of people in positions of authority or recognition within an organization

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

raq

-0.17

inel

-0.16

 Beit

-0.15

 Hamas

-0.15

Sly

-0.15

ingroup

-0.14

 Sting

-0.14

aeda

-0.14

entai

-0.14

Ya

-0.14

POSITIVE LOGITS

 Patel

0.24

 Indian

0.20

jee

0.20

 Indians

0.19

 Bind

0.18

Indian

0.17

 Gupta

0.17

bind

0.17

 Chop

0.17

 bind

0.17

Activations Density 0.251%

mentions of people in positions of authority or recognition within an organization

No Comments

No Known Activations