INDEX

Explanations

elements related to film and literary forms, particularly focusing on characters and narrative components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

Ã´n

-0.25

 Rosen

-0.19

 contato

-0.17

Ã´m

-0.16

 Chung

-0.16

Ãªn

-0.16

 controle

-0.16

spr

-0.15

 commitment

-0.15

Og

-0.14

POSITIVE LOGITS

Ã³nico

0.31

 activ

0.23

 actividades

0.22

 afect

0.21

 gÃ©

0.21

Ã©n

0.21

Ã³nica

0.21

 contacto

0.20

 gÃ©n

0.20

Ã³n

0.20

Activations Density 0.024%

elements related to film and literary forms, particularly focusing on characters and narrative components

No Comments

No Known Activations