INDEX

Explanations

references to specific numerical values and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ksam

-0.17

otlin

-0.17

oref

-0.16

orgot

-0.16

jspx

-0.15

vat

-0.15

eming

-0.14

cisi

-0.14

ogn

-0.14

/docs

-0.14

POSITIVE LOGITS

0.31

 pent

0.28

 Pent

0.28

äºĶ

0.27

 five

0.27

five

0.26

-five

0.25

 Five

0.25

ï

0.24

 Ð¿ÑıÑĤÑĮ

0.24

Activations Density 0.151%

references to specific numerical values and statistics

No Comments

No Known Activations