INDEX

Explanations

the word "using" and related programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

-0.16

-0.15

aeda

-0.15

 Wenger

-0.14

 philippines

-0.14

 proportion

-0.14

erif

-0.14

POSITIVE LOGITS

 Newtonsoft

0.33

 Xunit

0.30

 UnityEngine

0.29

 System

0.28

 NUnit

0.26

 Microsoft

0.24

 UnityEditor

0.24

 TMPro

0.23

 static

0.23

 AutoMapper

0.23

Activations Density 0.009%

the word "using" and related programming constructs

No Comments

No Known Activations