INDEX

Explanations

statements related to personal or professional announcements 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 @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

His

-0.27

 Himself

-0.26

His

-0.22

Him

-0.20

 oneself

-0.19

 Ø¥ÙĦÙĬÙĩ

-0.17

 Jeho

-0.16

 ÐĻÐ¾Ð³Ð¾

-0.16

 ÐķÐ³Ð¾

-0.16

ä»ĸçļĦ

-0.15

POSITIVE LOGITS

he

0.50

he

0.45

HE

0.35

hed

0.34

hc

0.32

0.30

_he

0.30

 Ð¾Ð½

0.29

HE

0.29

hes

0.29

Activations Density 0.423%

statements related to personal or professional announcements and experiences

No Comments

No Known Activations