INDEX

Explanations

references to bibliographic entries and sources

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

ationToken

-0.17

processable

-0.16

wyn

-0.15

ToOne

-0.15

ç½®

-0.15

-License

-0.15

rench

-0.14

-labelledby

-0.14

?url

-0.14

POSITIVE LOGITS

lio

0.24

oteca

0.21

oth

0.21

lical

0.18

Î»Î¹Î¿

0.18

ItemSelected

0.18

bero

0.17

otec

0.17

Bib

0.17

eral

0.16

Activations Density 0.005%

references to bibliographic entries and sources

No Comments

No Known Activations