INDEX

Explanations

subjects and objects in contexts related to regulations and accountability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 McMahon

-0.15

amik

-0.15

 Machinery

-0.14

ALAR

-0.14

imer

-0.14

adena

-0.14

mile

-0.14

ziej

-0.14

 Millet

-0.14

 Merchant

-0.13

POSITIVE LOGITS

mus

0.46

 must

0.41

 muss

0.34

 much

0.33

must

0.32

 mush

0.32

mu

0.31

Mus

0.31

 Must

0.30

Mus

0.29

Activations Density 0.078%

subjects and objects in contexts related to regulations and accountability

No Comments

No Known Activations