INDEX

Explanations

legal terminology related to motions and court rulings

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

zek

-0.16

aki

-0.15

 autos

-0.15

PRESSION

-0.15

umer

-0.14

 AttributeSet

-0.14

umper

-0.14

ellen

-0.13

ÙĪØ³ÛĮ

-0.13

ERSION

-0.13

POSITIVE LOGITS

0.17

 Guerr

0.14

spark

0.14

esto

0.14

neau

0.14

.GUI

0.14

aleigh

0.13

ascar

0.13

acos

0.13

Activations Density 0.027%

legal terminology related to motions and court rulings

No Comments

No Known Activations