INDEX

Explanations

references to positions of authority or leadership roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

grily

-0.19

ÑĥÑĢÑģ

-0.17

sik

-0.16

eso

-0.15

Ø§ÙĨØ³

-0.15

ought

-0.15

riad

-0.14

Î´Î¿

-0.14

sak

-0.14

existent

-0.14

POSITIVE LOGITS

person

0.47

persons

0.34

woman

0.32

manship

0.27

PERSON

0.26

mans

0.25

 person

0.24

man

0.23

lift

0.22

Person

0.22

Activations Density 0.014%

references to positions of authority or leadership roles

No Comments

No Known Activations