INDEX

Explanations

phrases indicating personal experiences or opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 itself

-0.16

st

-0.16

lopen

-0.16

lx

-0.16

umes

-0.14

 Moines

-0.14

 themselves

-0.14

 nous

-0.14

lv

-0.14

 yourselves

-0.14

POSITIVE LOGITS

 myself

0.34

’m

0.33

'm

0.30

’ve

0.27

've

0.27

 Ð±ÑĥÐ´Ñĥ

0.27

am

0.25

’ll

0.22

/my

0.22

 jsem

0.21

Activations Density 0.463%

phrases indicating personal experiences or opinions

No Comments

No Known Activations

phrases indicating personal experiences or opinions

No Comments

No Known Activations