INDEX

Explanations

references to legal analysis and court opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ì§¸

-0.16

-caret

-0.14

Documentation

-0.14

urban

-0.14

_fence

-0.13

æķ·

-0.13

ventario

-0.13

éľ

-0.13

Narr

-0.13

ÙĪØ²

-0.13

POSITIVE LOGITS

 patent

0.34

 Patent

0.34

PT

0.32

 patents

0.28

PT

0.25

 invalid

0.24

 district

0.22

pat

0.22

 institution

0.21

 Alice

0.21

Activations Density 0.014%

references to legal analysis and court opinions

No Comments

No Known Activations