INDEX

Explanations

phrases that indicate information or guidance about what one should know regarding a topic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

edb

-0.14

 Rockefeller

-0.14

 fortunes

-0.14

izik

-0.13

zÄħd

-0.13

à¸£à¸ĩ

-0.13

Mahon

-0.13

oris

-0.13

ocz

-0.13

acers

-0.13

POSITIVE LOGITS

 about

0.19

about

0.18

 About

0.14

-about

0.14

ird

0.14

hole

0.14

/use

0.14

.ai

0.14

About

0.14

StandardItem

0.14

Activations Density 0.016%

phrases that indicate information or guidance about what one should know regarding a topic

No Comments

No Known Activations