INDEX

Explanations

concepts related to rules and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

.parallel

-0.16

 fore

-0.15

igmoid

-0.15

Î»Î»Î±

-0.15

.Rad

-0.14

Ent

-0.14

icl

-0.14

ãĤ¸ãĤ¢

-0.14

 åĮĸ

-0.14

Î¾Î¹

-0.14

POSITIVE LOGITS

emas

0.16

_STMT

0.16

Ind

0.15

ind

0.15

Ø¨Ø§Ø±

0.15

ASH

0.15

Ash

0.14

ash

0.14

-ind

0.14

ind

0.14

Activations Density 0.035%

concepts related to rules and regulations

No Comments

No Known Activations