INDEX

Explanations

legal terminology and references related to court 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

ì§¸

-0.17

uga

-0.15

zed

-0.15

nig

-0.15

 Fant

-0.15

_fence

-0.14

 Grat

-0.14

pour

-0.14

 cling

-0.14

urban

-0.14

POSITIVE LOGITS

 Patent

0.26

PT

0.26

 patent

0.25

 Alice

0.22

 Hatch

0.21

 invalid

0.21

PT

0.21

Alice

0.20

 patents

0.20

 institution

0.18

Activations Density 0.013%

legal terminology and references related to court decisions

No Comments

No Known Activations