INDEX

Explanations

legal terminology related to court cases and lawsuits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Fetcher

-0.17

Î»Î¬

-0.16

unic

-0.15

RetVal

-0.15

Setup

-0.15

ãĥ¼ãĥĸãĥ«

-0.14

 unic

-0.14

.StackTrace

-0.14

/stretch

-0.14

 appellate

-0.13

POSITIVE LOGITS

 dismissal

0.32

dismiss

0.29

 dismiss

0.29

 dismissing

0.29

 motions

0.27

 summary

0.27

 dismissed

0.26

.dismiss

0.25

summary

0.24

 Motion

0.24

Activations Density 0.134%

legal terminology related to court cases and lawsuits

No Comments

No Known Activations