INDEX

Explanations

phrases related to recommendations and invitations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Ø·Ø±

-0.15

ãģŁãģĹ

-0.14

 meaning

-0.12

Including

-0.12

ãĢĤä½Ĩ

-0.12

meaning

-0.12

Ð¿Ð°ÑĤ

-0.12

Lol

-0.12

dik

-0.12

INCLUDING

-0.12

POSITIVE LOGITS

 yourself

0.38

 yourselves

0.33

if

0.32

 sometime

0.29

 Yourself

0.27

 while

0.24

 anytime

0.23

for

0.23

or

0.23

if

0.22

Activations Density 0.181%

phrases related to recommendations and invitations

No Comments

No Known Activations