INDEX

Explanations

programming-related terms and structures, particularly related to data types and method returns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

udas

-0.15

 Keystone

-0.14

equ

-0.14

uff

-0.14

 Thomson

-0.14

phy

-0.13

Î¿Î½

-0.13

ossa

-0.13

gee

-0.13

du

-0.13

POSITIVE LOGITS

plib

0.18

adow

0.16

uiltin

0.15

arer

0.15

eyi

0.14

Ńå·ŀ

0.14

ÑĭÐ»

0.14

alytics

0.14

 há»Ļi

0.14

åŃ£

0.14

Activations Density 0.032%

programming-related terms and structures, particularly related to data types and method returns

No Comments

No Known Activations