INDEX

Explanations

references to time and scheduling related to events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

iphy

-0.17

eba

-0.16

azer

-0.16

ÙĨØ¯Ú¯ÛĮ

-0.15

arkan

-0.15

duino

-0.14

icut

-0.14

ifa

-0.14

 Succ

-0.14

 ÐĴÐ»Ð°Ð´Ð¸

-0.14

POSITIVE LOGITS

 Walt

0.31

 Disney

0.30

 Magic

0.26

 Animal

0.25

Magic

0.25

Disney

0.24

 Mickey

0.24

 Orlando

0.23

 resorts

0.22

 resort

0.22

Activations Density 0.032%

references to time and scheduling related to events

No Comments

No Known Activations