INDEX

Explanations

keywords and phrases related to safety, clarity, and effectiveness in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

for

-0.35

 Ð´Ð»Ñı

-0.25

for

-0.24

 untuk

-0.24

 Î³Î¹Î±

-0.23

for

-0.23

 pentru

-0.22

 fÃ¼r

-0.22

ä¸º

-0.21

 voor

-0.21

POSITIVE LOGITS

 purposes

0.81

 sake

0.79

 purpose

0.41

 reasons

0.39

 PURPOSE

0.33

purpose

0.32

æĿ¥è¯´

0.31

Purpose

0.30

 reason

0.29

èĢĮ

0.29

Activations Density 0.833%

keywords and phrases related to safety, clarity, and effectiveness in various contexts

No Comments

No Known Activations