INDEX

Explanations

names of individuals and their affiliations or roles, particularly in the context of events or incidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ieten

-0.16

engers

-0.16

áº·n

-0.15

 Fallon

-0.15

 Bilg

-0.15

/sites

-0.14

ehr

-0.14

egin

-0.14

platz

-0.14

depend

-0.14

POSITIVE LOGITS

 Williams

0.25

 Jackson

0.24

 Washington

0.23

 Hairst

0.21

 Robinson

0.21

 Brown

0.20

 Harris

0.20

 Johnson

0.19

Williams

0.19

 ÐĴÐ°ÑĪ

0.19

Activations Density 0.235%

names of individuals and their affiliations or roles, particularly in the context of events or incidents

No Comments

No Known Activations