INDEX

Explanations

instances of the word "document"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

iling

-0.19

igel

-0.17

ps

-0.16

brook

-0.15

iting

-0.15

ighth

-0.14

ÙħØ§

-0.14

Ìī

-0.14

ÌĢ

-0.14

aching

-0.14

POSITIVE LOGITS

ations

0.32

arian

0.23

arians

0.23

aÃ§Ã£o

0.23

ually

0.22

BuilderFactory

0.21

alist

0.20

ary

0.19

edly

0.19

acion

0.19

Activations Density 0.054%

instances of the word "document"

No Comments

No Known Activations