INDEX

Explanations

punctuation marks and article header elements

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

 source

-0.15

Labels

-0.14

rvine

-0.14

leDb

-0.14

eparator

-0.14

ãĤ«ãĥĨãĤ´ãĥª

-0.14

 thÃ¹

-0.14

áº©u

-0.14

 labels

-0.13

source

-0.13

POSITIVE LOGITS

Ping

0.44

 Ping

0.35

 ping

0.27

_ping

0.26

Reply

0.23

âĨĲ

0.21

Previous

0.21

 Reply

0.20

Notice

0.19

 says

0.18

Activations Density 0.043%

punctuation marks and article header elements

No Comments

No Known Activations