INDEX

Explanations

references to technical or programming-related terms and configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Ø±Ø§Ùģ

-0.17

oose

-0.15

 overcrow

-0.15

SV

-0.14

 overse

-0.13

Dot

-0.13

ffa

-0.13

Aggregate

-0.13

.Singleton

-0.13

uard

-0.13

POSITIVE LOGITS

Ã¤dchen

0.15

wie

0.14

irie

0.14

ASN

0.14

uger

0.14

quets

0.14

æķ

0.14

esiz

0.14

Ã¢ng

0.14

 Mant

0.13

Activations Density 0.017%

references to technical or programming-related terms and configurations

No Comments

No Known Activations