INDEX

Explanations

code documentation and parameter annotations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

folk

-0.15

arrant

-0.14

ira

-0.14

 folk

-0.14

á»ī

-0.14

Æ°á»Ľ

-0.14

dr

-0.14

 dispos

-0.13

é¼

-0.13

POSITIVE LOGITS

ãĥ«ãĥķ

0.17

ylland

0.16

YYS

0.16

uars

0.15

 ReSharper

0.14

 AndAlso

0.14

undler

0.14

AMESPACE

0.14

PropertyChanged

0.13

arkan

0.13

Activations Density 0.015%

code documentation and parameter annotations

No Comments

No Known Activations