INDEX

Explanations

references to fairness or equity in various contexts

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

elho

-0.17

pheres

-0.16

owo

-0.15

obia

-0.15

eve

-0.15

ĤŃ

-0.15

endor

-0.14

gia

-0.14

sWith

-0.14

stag

-0.14

POSITIVE LOGITS

yt

0.39

ground

0.34

weather

0.33

grounds

0.33

er

0.28

ies

0.27

fax

0.27

child

0.26

play

0.25

banks

0.25

Activations Density 0.029%

references to fairness or equity in various contexts

No Comments

No Known Activations