INDEX

Explanations

references to the Supreme Court and its decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

laus

-0.16

umann

-0.16

Ø§ÙĨÙĩ

-0.15

.Properties

-0.15

ÎŃ

-0.14

ool

-0.13

esto

-0.13

á»Ń

-0.13

wy

-0.13

WARDS

-0.13

POSITIVE LOGITS

 Court

0.43

 court

0.36

Court

0.35

 COURT

0.31

court

0.27

-court

0.27

ourt

0.25

Ct

0.24

 Cour

0.21

 Cout

0.20

Activations Density 0.012%

references to the Supreme Court and its decisions

No Comments

No Known Activations