INDEX

Explanations

phrases related to legal proceedings and judicial outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ulis

-0.15

tered

-0.15

onso

-0.15

ritten

-0.14

iens

-0.14

overy

-0.14

ĵåĲį

-0.13

alace

-0.13

opsis

-0.13

ropa

-0.13

POSITIVE LOGITS

rem

0.26

arr

0.26

 released

0.25

 extrad

0.24

 rear

0.24

 tried

0.23

 formally

0.23

 condition

0.23

 freed

0.23

 sentenced

0.22

Activations Density 0.050%

phrases related to legal proceedings and judicial outcomes

No Comments

No Known Activations