INDEX

Explanations

references to categories or classifications of items and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

rawn

-0.16

Ø°Ùĩ

-0.15

anke

-0.15

ced

-0.15

 Partnership

-0.14

eps

-0.14

ehler

-0.14

aked

-0.14

Ø§ÙĨØ³

-0.14

itel

-0.14

POSITIVE LOGITS

ogue

0.17

etc

0.16

indows

0.16

conti

0.16

ëŀĮ

0.15

Hol

0.15

enie

0.15

SSIP

0.15

 creat

0.14

 Crowley

0.14

Activations Density 0.076%

references to categories or classifications of items and experiences

No Comments

No Known Activations