INDEX

Explanations

questions or statements expressing uncertainty or inquiry about the existence or availability of something

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

aphrag

-0.16

awe

-0.15

andr

-0.14

emann

-0.14

ertain

-0.14

lic

-0.13

erna

-0.13

ÏĢÎ¿Î½

-0.13

Ĥæķ°

-0.13

arser

-0.13

POSITIVE LOGITS

.synthetic

0.15

Ĵ

0.14

ofi

0.14

 ØŃÙĬ

0.14

Å¯st

0.14

ibaba

0.13

nyder

0.13

ÑĥÑĪÐºÐ¸

0.13

eldom

0.13

bos

0.13

Activations Density 0.010%

questions or statements expressing uncertainty or inquiry about the existence or availability of something

No Known Activations