INDEX

Explanations

references to prior mentions or acknowledgments within 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 @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

lette

-0.15

SingleNode

-0.14

mercial

-0.14

ufac

-0.14

auge

-0.13

Ã¨o

-0.13

uctor

-0.13

ernes

-0.13

lor

-0.13

 innocence

-0.13

POSITIVE LOGITS

 prav

0.15

 Mall

0.14

Gap

0.14

 bure

0.14

etta

0.14

argin

0.14

otron

0.14

ahlen

0.14

0.13

Activations Density 0.054%

references to prior mentions or acknowledgments within the text

No Comments

No Known Activations