INDEX

Explanations

references to movie premieres and celebrity events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

abr

-0.17

resa

-0.16

è®

-0.16

nore

-0.15

ubs

-0.15

inton

-0.15

rava

-0.14

icio

-0.14

 Purdue

-0.14

ackbar

-0.14

POSITIVE LOGITS

 photoc

0.27

red

0.26

 premiere

0.26

 arrivals

0.25

 press

0.24

 premier

0.22

 prem

0.21

 premiÃ¨re

0.21

/red

0.20

red

0.19

Activations Density 0.064%

references to movie premieres and celebrity events

No Comments

No Known Activations