INDEX

Explanations

legal terminology related to charges and offenses

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

orrent

-0.17

/Gate

-0.16

rary

-0.16

abase

-0.16

zc

-0.15

iode

-0.15

ofilm

-0.14

abay

-0.14

_CF

-0.14

 Lage

-0.14

POSITIVE LOGITS

 failure

0.22

 disorder

0.22

 Poss

0.21

 possession

0.21

 simple

0.21

 Disorder

0.20

 Failure

0.20

 speeding

0.19

 driving

0.19

 litter

0.19

Activations Density 0.014%

legal terminology related to charges and offenses

No Comments

No Known Activations