INDEX

Explanations

mentions of the letter 'N' or the character 'N'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

/Dk

-0.18

_None

-0.16

âĢŀN

-0.16

MBED

-0.15

IENT

-0.15

Ø§Ø¬Ø±

-0.14

ãĢĩ

-0.14

NK

-0.14

loquent

-0.14

arrings

-0.14

POSITIVE LOGITS

ational

0.27

ationally

0.26

orth

0.24

ash

0.23

apa

0.23

atl

0.22

ATIONAL

0.22

ancy

0.21

urs

0.20

YS

0.20

Activations Density 0.024%

mentions of the letter 'N' or the character 'N'

No Comments

No Known Activations