INDEX

Explanations

phrases related to problem-solving or figuring things out

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

/about

-0.16

upa

-0.15

 Sebastian

-0.15

uali

-0.15

aeda

-0.14

elsey

-0.14

gow

-0.14

 subsequ

-0.14

/ne

-0.14

OW

-0.13

POSITIVE LOGITS

 figured

0.38

 figure

0.37

fig

0.33

figure

0.31

fig

0.30

-figure

0.28

 figures

0.28

FIG

0.27

FIG

0.27

figures

0.26

Activations Density 0.017%

phrases related to problem-solving or figuring things out

No Comments

No Known Activations