INDEX

Explanations

references to critical moments or key points in a discussion

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

 this

-0.26

 these

-0.23

this

-0.22

these

-0.20

è¿Ļ

-0.19

è¿Ļä¸Ģ

-0.19

éĢĻ

-0.17

(this

-0.17

owell

-0.17

 ÑįÑĤÐ¾Ð¼

-0.17

POSITIVE LOGITS

-ÑĤÐ¾

0.20

à¹Ģà¸Ńà¸ĩ

0.16

-ci

0.15

aways

0.15

ina

0.15

 nejen

0.15

overs

0.14

jÅ¡ÃŃ

0.14

åĳ¢

0.14

 ustanov

0.13

Activations Density 0.111%

references to critical moments or key points in a discussion

No Comments

No Known Activations