INDEX

Explanations

elements related to programming or technical inquiries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

å¤®

-0.16

undi

-0.16

iesel

-0.15

odynam

-0.15

ÐºÐ¾ÑĢ

-0.15

ollower

-0.14

ylvania

-0.14

sect

-0.14

IPS

-0.14

apult

-0.14

POSITIVE LOGITS

 Chat

0.21

 chat

0.20

(Chat

0.17

 chatting

0.17

Chat

0.17

chat

0.16

 chats

0.16

-chat

0.16

UPPORT

0.16

enger

0.16

Activations Density 0.001%

elements related to programming or technical inquiries

No Comments

No Known Activations