INDEX

Explanations

terms related to the legal profession and law-related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 Jeho

-0.17

IPP

-0.17

DM

-0.15

uster

-0.15

reta

-0.14

 Blitz

-0.14

ered

-0.14

 right

-0.14

amin

-0.14

POSITIVE LOGITS

licken

0.16

edl

0.15

mojom

0.15

;/*

0.14

andid

0.14

ÐµÐ½Ð·

0.14

elease

0.14

ysize

0.14

.IsNullOr

0.14

anton

0.14

Activations Density 0.750%

terms related to the legal profession and law-related activities

No Comments

No Known Activations