INDEX

Explanations

instances of the word "Object" in various contexts related to programming and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

esin

-0.15

 Vill

-0.15

unday

-0.15

cond

-0.15

ÂŃing

-0.14

ÑĢÑĥÐ±

-0.14

RAL

-0.14

arbon

-0.13

Erd

-0.13

 saddle

-0.13

POSITIVE LOGITS

cir

0.17

 Miracle

0.15

acock

0.15

 ripe

0.14

 Ø¢Ø²

0.14

arence

0.14

 Shirt

0.14

 Hobby

0.14

awei

0.13

iface

0.13

Activations Density 0.006%

instances of the word "Object" in various contexts related to programming and data structures

No Comments

No Known Activations