INDEX

Explanations

numerical values or data representing quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

-0.16

 Ãľst

-0.15

achel

-0.14

udes

-0.14

oley

-0.14

 ÅĤ

-0.13

ufs

-0.13

Ð°ÑĢÑĩ

-0.13

arty

-0.13

POSITIVE LOGITS

ÛĢ

0.17

atoria

0.15

aimassage

0.14

_pdata

0.14

ypi

0.14

istrator

0.14

ÑĢÑĥÐ³

0.14

Ø§ÛĮÙĩ

0.14

Ctrls

0.14

phanumeric

0.13

Activations Density 0.178%

numerical values or data representing quantities

No Comments

No Known Activations