INDEX

Explanations

frequently occurring terms related to common inquiries or frequently asked questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ipeg

-0.14

-Sah

-0.14

Vendor

-0.14

à¤¾à¤ī

-0.14

(æľĪ

-0.14

ÅĻes

-0.13

CHandle

-0.13

vendor

-0.13

ouncements

-0.13

 Memo

-0.13

POSITIVE LOGITS

 Mister

0.23

 shortcuts

0.20

Bod

0.19

 Masters

0.18

 masters

0.18

 health

0.17

 Acceler

0.17

 Shortcut

0.17

Mr

0.17

 power

0.17

Activations Density 0.000%

frequently occurring terms related to common inquiries or frequently asked questions

No Comments

No Known Activations