INDEX

Explanations

instructions related to software settings and configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

à¥Ģà¤§

-0.16

itel

-0.15

ekil

-0.15

ubl

-0.14

Ø¨Ø§Ø´

-0.14

odega

-0.14

/*č↵

-0.14

ajan

-0.14

å¡ļ

-0.13

LTR

-0.13

POSITIVE LOGITS

åĭ

0.24

 Advanced

0.20

Advanced

0.19

 radio

0.19

_advanced

0.18

 åĭ

0.18

 General

0.18

vanced

0.17

 advanced

0.17

advanced

0.17

Activations Density 0.078%

instructions related to software settings and configurations

No Comments

No Known Activations