INDEX

Explanations

mentions of quotes and quotations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

StateException

-0.18

Lyn

-0.15

elta

-0.15

orsi

-0.15

 Damian

-0.15

-0.14

combe

-0.14

ERN

-0.14

trak

-0.14

azio

-0.14

POSITIVE LOGITS

onto

0.15

 eÅŁ

0.15

Ī

0.14

bildung

0.14

cdr

0.14

 personals

0.14

ìĭ¸

0.14

fang

0.14

aires

0.13

éĹŃ

0.13

Activations Density 0.023%

mentions of quotes and quotations

No Comments

No Known Activations