INDEX

Explanations

references to the letter "V" in various contexts, possibly indicating an emphasis on a particular topic or category associated with that letter

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

chu

-0.18

Å¡ka

-0.15

fis

-0.14

cerr

-0.14

mere

-0.14

ritte

-0.14

pter

-0.14

AndUpdate

-0.13

Gh

-0.13

Geh

-0.13

POSITIVE LOGITS

amp

0.23

HS

0.21

ulture

0.21

SCO

0.20

logging

0.19

ix

0.18

apid

0.18

udu

0.18

amps

0.18

room

0.18

Activations Density 0.031%

references to the letter "V" in various contexts, possibly indicating an emphasis on a particular topic or category associated with that letter

No Comments

No Known Activations