INDEX

Explanations

specific details and structure related to events, exhibitions, or presentations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

PropertyDescriptor

-0.15

å«

-0.14

 máº·t

-0.13

 Trem

-0.13

abet

-0.13

 lint

-0.13

mal

-0.13

 chart

-0.13

roz

-0.13

edl

-0.13

POSITIVE LOGITS

ioxide

0.17

 ÐļÐ¾Ð»Ð¸

0.16

endale

0.15

ilha

0.15

ously

0.14

Ãłnh

0.14

uche

0.14

izza

0.14

)(↵

0.13

 Cooling

0.13

Activations Density 0.541%

specific details and structure related to events, exhibitions, or presentations

No Comments

No Known Activations