INDEX

Explanations

technical discussions about software and hardware compatibility issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

afx

-0.17

emento

-0.16

 Firebase

-0.16

_dll

-0.15

_UNIX

-0.15

vue

-0.15

cordova

-0.14

 PowerShell

-0.14

Microsoft

-0.14

 JetBrains

-0.14

POSITIVE LOGITS

 Gent

0.23

CVS

0.21

 Myth

0.21

 myth

0.20

 patches

0.20

 gent

0.19

gent

0.18

 Patch

0.18

subpackage

0.18

 patch

0.17

Activations Density 0.153%

technical discussions about software and hardware compatibility issues

No Comments

No Known Activations