INDEX

Explanations

references to timeframes and significant milestones

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

eenth

-0.17

-0.16

Fif

-0.16

 twenties

-0.15

 åįģ

-0.15

 twentieth

-0.15

Ten

-0.15

_ten

-0.15

Ð»Ñİ

-0.15

TEN

-0.15

POSITIVE LOGITS

 half

0.26

 three

0.23

two

0.21

 cent

0.20

 four

0.19

 nearly

0.19

 Cent

0.19

åįĬ

0.19

 CENT

0.19

 quarter

0.18

Activations Density 0.049%

references to timeframes and significant milestones

No Comments

No Known Activations