INDEX

Explanations

words related to preservation and documentation

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

 subt

-0.17

umba

-0.16

anguages

-0.15

letes

-0.14

uji

-0.14

izzato

-0.14

agher

-0.14

ments

-0.14

elder

-0.14

Î²Î¬

-0.14

POSITIVE LOGITS

aciÃ³n

0.38

iciÃ³n

0.29

aci

0.28

acio

0.26

aÃ§Ã£o

0.26

ACIÃĵN

0.26

uciÃ³n

0.25

ciÃ³n

0.25

azione

0.24

pciÃ³n

0.24

Activations Density 0.041%

words related to preservation and documentation

No Comments

No Known Activations