INDEX

Explanations

phrases and contractions related to possession or belonging

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

thon

-0.20

want

-0.16

oft

-0.15

ubu

-0.15

liers

-0.15

ogue

-0.15

åħ¼

-0.14

liest

-0.14

owej

-0.14

 Want

-0.14

POSITIVE LOGITS

 face

0.32

 hope

0.29

 suppose

0.28

 faces

0.21

 Encrypt

0.21

hope

0.21

 hoping

0.21

face

0.21

see

0.20

 assume

0.20

Activations Density 0.023%

phrases and contractions related to possession or belonging

No Comments

No Known Activations