INDEX

Explanations

code and programming-related terminology

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

arro

-0.15

otti

-0.14

amic

-0.14

nim

-0.14

perator

-0.13

 å§

-0.13

sha

-0.13

Fore

-0.13

 Wien

-0.13

illac

-0.13

POSITIVE LOGITS

 kernel

0.28

 Kernel

0.23

_kernel

0.22

 Linux

0.22

/kernel

0.21

 kernels

0.21

kernel

0.21

 ioctl

0.20

 IOCTL

0.20

 mmap

0.19

Activations Density 0.041%

code and programming-related terminology

No Comments

No Known Activations