INDEX

Explanations

words and phrases associated with brightness and positivity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

hattan

-0.18

hiro

-0.17

ÑģÑı

-0.16

nd

-0.16

ather

-0.15

oooo

-0.15

hort

-0.15

Ð³Ðµ

-0.15

BLE

-0.14

isy

-0.14

POSITIVE LOGITS

ening

0.40

ened

0.36

eners

0.28

-eyed

0.26

ens

0.25

ener

0.23

en

0.23

enment

0.22

 eyed

0.21

enin

0.21

Activations Density 0.028%

words and phrases associated with brightness and positivity

No Comments

No Known Activations