INDEX

Explanations

references to various occupations and roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

------+------+

-0.15

#================================================================

-0.13

ãģ«ãģĭ

-0.13

ìĩ

-0.13

ê°¤

-0.13

zÃ¡

-0.12

Ã¤ng

-0.12

depart

-0.11

[assembly

-0.11

ukkan

-0.11

POSITIVE LOGITS

 from

1.03

from

0.82

 frÃ¥n

0.71

 FROM

0.70

 tá»«

0.69

	from

0.68

 dari

0.67

à¸Īà¸²à¸ģ

0.65

 From

0.62

_from

0.62

Activations Density 0.505%

references to various occupations and roles

No Comments

No Known Activations