INDEX

Explanations

references to rankings and evaluations of academic programs

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

/wiki

-0.17

(æľ¨

-0.17

ewire

-0.15

(æ°´

-0.15

ainen

-0.15

eway

-0.15

Ð»Ð°Ð·

-0.14

 wiki

-0.13

/unit

-0.13

ovna

-0.13

POSITIVE LOGITS

 World

1.01

World

0.93

 world

0.85

 WORLD

0.83

world

0.77

-world

0.74

_world

0.73

ä¸ĸçķĮ

0.72

 Worlds

0.66

.world

0.65

Activations Density 0.265%

references to rankings and evaluations of academic programs

No Comments

No Known Activations