INDEX

Explanations

structured data or formats typical to programming, especially around logging or configuration settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

akedown

-0.15

vala

-0.15

nesc

-0.15

åľº

-0.14

xec

-0.14

eÄį

-0.14

ë°

-0.14

fk

-0.14

Ø²Ø±

-0.13

ifar

-0.13

POSITIVE LOGITS

extView

0.16

iot

0.16

ableView

0.15

yp

0.14

 prostitutas

0.14

pulse

0.14

ahr

0.13

Ø¨ÙĪØ§Ø³Ø·Ø©

0.13

iph

0.13

 Constructors

0.13

Activations Density 0.112%

structured data or formats typical to programming, especially around logging or configuration settings

No Comments

No Known Activations