INDEX

Explanations

names of individuals associated with the entertainment industry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

-_

-0.18

;if

-0.17

-${

-0.16

–↵↵

-0.16

_-

-0.16

-|

-0.15

-↵↵

-0.15

-/

-0.15

-</

-0.15

-'.$

-0.14

POSITIVE LOGITS

 among

0.41

 amongst

0.39

and

0.34

among

0.30

 along

0.28

 plus

0.28

 alongside

0.25

amd

0.24

etc

0.24

and

0.23

Activations Density 0.181%

names of individuals associated with the entertainment industry

No Comments

No Known Activations