INDEX

Explanations

references to coding and data structures

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

NGX

-0.15

utos

-0.14

istogram

-0.14

çļĦæĥħ

-0.14

ä¼ı

-0.14

.threshold

-0.13

æ£

-0.13

>{!!

-0.13

æ¥

-0.13

 Motion

-0.13

POSITIVE LOGITS

 functional

0.29

 Functional

0.27

 Scheme

0.26

Functional

0.23

Clo

0.23

 Curry

0.23

DSL

0.21

FP

0.21

Lis

0.21

-functional

0.21

Activations Density 0.043%

references to coding and data structures

No Comments

No Known Activations

references to coding and data structures

No Comments

No Known Activations