INDEX

Explanations

references to legal proceedings and criminal activity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

-0.15

atism

-0.15

 inaugur

-0.14

èª

-0.14

lisi

-0.14

 local

-0.14

sue

-0.14

ufac

-0.14

çīĮ

-0.14

 noct

-0.14

POSITIVE LOGITS

 defense

0.33

 defence

0.31

-defense

0.28

defense

0.27

 Defense

0.24

Defense

0.24

 Defence

0.23

 prosecution

0.20

 jurors

0.19

 counsel

0.19

Activations Density 0.076%

references to legal proceedings and criminal activity

No Comments

No Known Activations