INDEX

Explanations

references to individuals or entities related to the legal or judicial system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

otor

-0.17

arias

-0.17

taire

-0.16

/meta

-0.15

yar

-0.15

usk

-0.15

 Pixels

-0.15

PEG

-0.15

atrix

-0.15

idas

-0.15

POSITIVE LOGITS

ollo

0.16

awah

0.14

enden

0.14

ent

0.14

pls

0.14

 >>↵↵

0.14

fg

0.14

tep

0.14

icht

0.14

 IService

0.14

Activations Density 0.066%

references to individuals or entities related to the legal or judicial system

No Comments

No Known Activations