INDEX

Explanations

coding concepts and terminology related to 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

eh

-0.16

amel

-0.15

omn

-0.15

ransition

-0.15

ncoder

-0.13

 paramet

-0.13

æĿ¡

-0.13

oya

-0.13

ourd

-0.13

 voucher

-0.13

POSITIVE LOGITS

 operations

0.34

 operation

0.33

 operators

0.32

è¿Ĳ

0.31

 Operation

0.31

operation

0.30

 Addition

0.29

 addition

0.29

 Operations

0.29

operations

0.28

Activations Density 0.135%

coding concepts and terminology related to programming

No Comments

No Known Activations