INDEX

Explanations

references to learning experiences and internships related to coding and programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 ComVisible

-0.16

.scalablytyped

-0.16

 oper

-0.15

ofs

-0.14

 Acrobat

-0.14

ãĥ³ãĥĨ

-0.14

VERR

-0.14

esModule

-0.14

swire

-0.13

omite

-0.13

POSITIVE LOGITS

 coding

0.40

 programming

0.38

 Coding

0.37

 Programming

0.35

 code

0.34

 Code

0.30

coding

0.30

Coding

0.30

Programming

0.30

Code

0.29

Activations Density 0.376%

references to learning experiences and internships related to coding and programming

No Comments

No Known Activations