INDEX

Explanations

references to specific roles, technologies, and systems related to organization and planning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

rh

-0.14

ë¡Ģ

-0.13

kop

-0.13

asl

-0.13

isher

-0.13

æīį

-0.13

Has

-0.13

Counts

-0.13

oline

-0.12

-has

-0.12

POSITIVE LOGITS

çļĦæĺ¯

0.29

is

0.25

å°±æĺ¯

0.23

 adalah

0.23

ï¼Įå°±æĺ¯

0.19

ï¼īãģ¯

0.18

ìŀ¥ìĿĢ

0.18

 include

0.18

 Ø¹Ø¨Ø§Ø±Øª

0.18

 lies

0.17

Activations Density 0.181%

references to specific roles, technologies, and systems related to organization and planning

No Comments

No Known Activations