INDEX

Explanations

references to object-oriented programming concepts and queries

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

Ø´Ùĩ

-0.17

mud

-0.15

 Scatter

-0.15

.visitMethod

-0.14

Ø³Ùĩ

-0.14

_DIV

-0.13

adol

-0.13

Mud

-0.13

Ø²Ø§

-0.13

omitempty

-0.13

POSITIVE LOGITS

 order

0.24

.order

0.24

 select

0.23

distinct

0.21

.select

0.21

 Dist

0.20

select

0.20

order

0.19

 distinct

0.19

.filter

0.19

Activations Density 0.010%

references to object-oriented programming concepts and queries

No Comments

No Known Activations