INDEX

Explanations

legal terms and references to regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 pard

-0.16

Ã±a

-0.16

 ÑĨÐ¸

-0.14

 pardon

-0.14

ander

-0.14

Zuk

-0.14

ationship

-0.13

ByUrl

-0.13

ç¤¾

-0.13

 xhttp

-0.13

POSITIVE LOGITS

mess

0.17

uard

0.17

isser

0.16

 Noel

0.16

isi

0.15

alamat

0.15

ipi

0.15

osi

0.15

ches

0.15

inspace

0.15

Activations Density 0.122%

legal terms and references to regulations

No Comments

No Known Activations