INDEX

Explanations

references to specific individuals or entities involved in a legal context

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

enger

-0.17

ucene

-0.16

rios

-0.15

Nonce

-0.15

borough

-0.15

isti

-0.15

visor

-0.14

âĸĪâĸĪâĸĪâĸĪ

-0.14

isci

-0.14

context

-0.14

POSITIVE LOGITS

icients

0.21

rane

0.19

reau

0.18

ition

0.17

-Cola

0.17

 incident

0.16

co

0.15

nty

0.15

ubar

0.15

esion

0.15

Activations Density 0.038%

references to specific individuals or entities involved in a legal context

No Comments

No Known Activations