INDEX

Explanations

references to prominent technologies, brands, or scientific concepts in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

istrovstvÃŃ

-0.19

.ribbon

-0.15

onis

-0.14

Ler

-0.14

anj

-0.14

 Curve

-0.14

curve

-0.14

 optimal

-0.14

enthal

-0.13

:///

-0.13

POSITIVE LOGITS

Justice

0.18

ampa

0.16

 Justice

0.15

SPA

0.14

 Mund

0.14

ynamo

0.14

loh

0.14

agna

0.14

VO

0.14

rosse

0.14

Activations Density 0.047%

references to prominent technologies, brands, or scientific concepts in the text

No Comments

No Known Activations