INDEX

Explanations

terms and phrases related to programming and coding structures

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

ÑĢÐ¸Ñĩ

-0.13

idor

-0.13

asti

-0.12

 Password

-0.12

orrent

-0.12

DeltaTime

-0.12

 NSIndexPath

-0.12

orda

-0.12

ÏĦÏģ

-0.12

\ActiveForm

-0.12

POSITIVE LOGITS

map

0.44

Map

0.40

map

0.38

 google

0.37

 maps

0.36

 Maps

0.36

Map

0.36

 marker

0.35

(map

0.35

 mapa

0.34

Activations Density 0.062%

terms and phrases related to programming and coding structures

No Comments

No Known Activations