INDEX

Explanations

mentions of legal charges and convictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 Arrest

-0.19

ictim

-0.17

 arrest

-0.17

 Mour

-0.15

 Alleg

-0.15

thon

-0.15

 allegations

-0.14

awks

-0.14

unta

-0.14

 arrests

-0.14

POSITIVE LOGITS

 conviction

0.33

 convictions

0.30

conv

0.27

 sentence

0.27

 Conv

0.26

Sentence

0.25

Conv

0.24

 convicted

0.24

 Sentence

0.23

 sentenced

0.23

Activations Density 0.073%

mentions of legal charges and convictions

No Comments

No Known Activations