INDEX

Explanations

legal terms and references to laws and regulations

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

erus

-0.16

agon

-0.15

Äł

-0.14

hawks

-0.14

bia

-0.14

 çĻ¼

-0.14

irim

-0.13

Denied

-0.13

 Chall

-0.13

loys

-0.13

POSITIVE LOGITS

 states

0.38

states

0.29

 sets

0.28

 bars

0.27

 spells

0.26

 specifies

0.25

 author

0.24

.states

0.24

 STATES

0.24

 Bars

0.23

Activations Density 0.204%

legal terms and references to laws and regulations

No Comments

No Known Activations

legal terms and references to laws and regulations

No Comments

No Known Activations