INDEX

Explanations

terms related to website functionality and user experience enhancements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ilians

-0.15

 Sharp

-0.15

elder

-0.15

-0.14

egt

-0.14

Ð½ÑıÑĤ

-0.14

Ð´Ñĥ

-0.14

apes

-0.14

ieri

-0.14

BCH

-0.13

POSITIVE LOGITS

 cookies

0.20

ÙĥÙĬ

0.16

 cookie

0.16

buz

0.15

Cookie

0.15

 ÑħÐ¾Ð»

0.15

 Cookies

0.15

anon

0.14

 rÃ³wn

0.14

0.13

Activations Density 0.144%

terms related to website functionality and user experience enhancements

No Comments

No Known Activations