INDEX

Explanations

phrases surrounding personal opinions and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

eczy

-0.18

uis

-0.17

ÑĩÐ¸Ð»Ð¸

-0.15

Ð´Ð¸Ð½Ð°

-0.14

stroy

-0.14

ury

-0.14

Ø§Øº

-0.14

AGIC

-0.14

 Burl

-0.14

DBG

-0.13

POSITIVE LOGITS

ISCO

0.16

isco

0.15

ignum

0.15

istrovstvÃŃ

0.15

åºķ

0.15

eness

0.14

å¾ģ

0.14

adele

0.13

enses

0.13

Ð°ÐºÑģ

0.13

Activations Density 0.245%

phrases surrounding personal opinions and experiences

No Comments

No Known Activations