INDEX

Explanations

phrases related to returning to a state of normalcy or routine

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

 lleg

-0.14

 demise

-0.13

áº¯t

-0.13

 attainment

-0.13

è©ŀ

-0.13

 ëĸ¨ìĸ´

-0.12

Ø§ÙĨØ§Øª

-0.12

ric

-0.12

 slightest

-0.12

Ð±ÑĥÑĤ

-0.12

POSITIVE LOGITS

 basics

0.42

 normal

0.38

 Basics

0.32

 square

0.30

normal

0.29

 whence

0.29

 sender

0.27

-normal

0.27

 NORMAL

0.27

 normals

0.27

Activations Density 0.104%

phrases related to returning to a state of normalcy or routine

No Comments

No Known Activations