INDEX

Explanations

references to legal proceedings and judicial decisions

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

 plaintiffs

-0.18

plaint

-0.17

 tort

-0.16

 suites

-0.16

 Plaint

-0.16

 plut

-0.16

 lawsuit

-0.15

 plaintiff

-0.15

azon

-0.14

criptors

-0.14

POSITIVE LOGITS

 ineffective

0.25

Bat

0.24

 collateral

0.23

 habe

0.23

Bat

0.21

PCR

0.20

 appointed

0.19

 Anders

0.19

 resent

0.18

 sentencing

0.18

Activations Density 0.067%

references to legal proceedings and judicial decisions

No Comments

No Known Activations