INDEX

Explanations

references to media and reporting entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Patreon

-0.15

_unsigned

-0.14

isu

-0.14

Ø®ÙĦ

-0.13

ilk

-0.13

arena

-0.13

usp

-0.13

.WriteHeader

-0.13

_SYM

-0.13

#=>

-0.13

POSITIVE LOGITS

 Related

0.18

PIX

0.17

 gallery

0.16

 RELATED

0.16

AOL

0.16

MORE

0.16

ÑıÐ¼

0.15

 Gallery

0.15

Related

0.15

 Associated

0.15

Activations Density 0.102%

references to media and reporting entities

No Comments

No Known Activations