INDEX

Explanations

articles and references to quantities

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

stup

-0.15

ëŀĢ

-0.13

--[

-0.13

pes

-0.13

ltk

-0.13

thora

-0.13

aes

-0.13

æŁĦ

-0.13

esi

-0.13

getVar

-0.13

POSITIVE LOGITS

 breeze

0.25

 struggle

0.23

 revelation

0.22

cin

0.22

bit

0.21

 disaster

0.21

 challenge

0.21

 blur

0.20

 pain

0.20

 pleasure

0.20

Activations Density 0.144%

articles and references to quantities

No Comments

No Known Activations