INDEX

Explanations

references to significant concepts or entities marked by the term "great" or related contextual importance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ÅĦ

-0.17

overe

-0.16

-Version

-0.14

uze

-0.14

zzo

-0.14

Aspect

-0.14

aven

-0.14

 onNext

-0.13

 situation

-0.13

 earliest

-0.13

POSITIVE LOGITS

-grand

0.29

atsby

0.26

coat

0.22

sword

0.20

 majority

0.20

(est

0.19

 dane

0.18

eur

0.17

oted

0.17

 powers

0.17

Activations Density 0.061%

references to significant concepts or entities marked by the term "great" or related contextual importance

No Comments

No Known Activations