INDEX

Explanations

phrases indicating new opportunities or possibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

dit

-0.15

ãĥ¼ãĥĨãĤ£

-0.15

ãĥ³ãĥĨãĤ£

-0.14

builtin

-0.14

hit

-0.14

dings

-0.14

utilus

-0.14

ego

-0.13

hits

-0.13

kaar

-0.13

POSITIVE LOGITS

 possibilities

0.31

 possibility

0.27

 opportunities

0.27

 possibilit

0.25

 POSSIBILITY

0.24

 opportunity

0.23

 opens

0.23

 opened

0.23

 moÅ¼li

0.21

opened

0.21

Activations Density 0.054%

phrases indicating new opportunities or possibilities

No Comments

No Known Activations