INDEX

Explanations

programming-related keywords and phrases associated with coding questions or issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

pleted

-0.16

aven

-0.16

onga

-0.15

_Abstract

-0.15

irit

-0.14

phere

-0.14

antro

-0.14

apor

-0.13

uger

-0.13

StandardItem

-0.13

POSITIVE LOGITS

Ã¨ge

0.14

Ø¹ÙĨ

0.14

tones

0.13

hod

0.13

GDK

0.13

herits

0.13

itness

0.13

è®¿

0.13

èĩ´

0.13

Ã¸re

0.13

Activations Density 1.296%

programming-related keywords and phrases associated with coding questions or issues

No Comments

No Known Activations