INDEX

Explanations

keywords related to legal actions and proceedings

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

Ton

-0.15

 Mile

-0.14

iner

-0.14

ivet

-0.14

Ã©rt

-0.14

 Petty

-0.14

plusplus

-0.14

zer

-0.14

 Hawkins

-0.14

UIApplication

-0.13

POSITIVE LOGITS

 Pais

0.16

essed

0.15

ĥĿ

0.15

Administr

0.14

 Administrative

0.14

Ð¾Ð³ÐµÐ½

0.14

fis

0.14

pec

0.14

dex

0.14

[[

0.14

Activations Density 0.007%

keywords related to legal actions and proceedings

No Comments

No Known Activations