INDEX

Explanations

legal terminology related to criminal 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 @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ekk

-0.15

ialog

-0.15

áº©y

-0.14

 forks

-0.14

 Marr

-0.14

Fu

-0.13

ACHINE

-0.13

ensor

-0.13

arent

-0.13

ãģĮãģĬ

-0.13

POSITIVE LOGITS

 charges

0.18

charges

0.17

igon

0.17

 charge

0.16

vap

0.16

.lib

0.16

unga

0.15

kv

0.15

oso

0.15

 upgraded

0.15

Activations Density 0.026%

legal terminology related to criminal charges and offenses

No Comments

No Known Activations