INDEX

Explanations

formatting and syntax elements related to programming and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

authors

-0.18

áºŃp

-0.17

 AUTHORS

-0.16

 Authors

-0.16

ifo

-0.16

Authors

-0.15

hell

-0.15

 authors

-0.15

eger

-0.15

oni

-0.15

POSITIVE LOGITS

ÙĨØ³

0.18

lich

0.15

Specifier

0.14

.opensource

0.14

Ä©nh

0.13

 æĳ

0.13

.addComponent

0.13

 Sawyer

0.13

âĻł

0.13

ardÄ±m

0.13

Activations Density 0.005%

formatting and syntax elements related to programming and documentation

No Comments

No Known Activations