INDEX

Explanations

punctuation marks and formatting elements in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

aminer

-0.17

geois

-0.16

ANNEL

-0.15

ì§ĢëıĦ

-0.14

Ð½Ð¾Ð¿

-0.14

 prostituer

-0.14

uz

-0.14

#ae

-0.14

uli

-0.14

KN

-0.14

POSITIVE LOGITS

ighter

0.16

cos

0.16

ervals

0.16

.dc

0.15

ckt

0.15

Ïİ

0.15

_codec

0.15

esModule

0.15

Bang

0.14

 full

0.14

Activations Density 0.003%

punctuation marks and formatting elements in the text

No Comments

No Known Activations