INDEX

Explanations

references to people

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

ÑĤÐ¾Ð²

-0.17

agar

-0.17

ugin

-0.16

logan

-0.16

strap

-0.15

izador

-0.15

áº¡n

-0.15

lems

-0.15

unger

-0.15

issing

-0.14

POSITIVE LOGITS

nel

0.28

nal

0.27

ajes

0.26

aggi

0.25

hood

0.23

nels

0.22

ality

0.21

ae

0.21

alia

0.20

ified

0.20

Activations Density 0.013%

references to people

No Comments

No Known Activations