INDEX

Explanations

references to film-related professions and projects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

.SaveChangesAsync

-0.14

Ø³ÙħØ©

-0.14

 Harness

-0.13

Ø¦Øª

-0.13

 Workshop

-0.13

iferay

-0.13

ISBN

-0.13

 Insecta

-0.13

aptive

-0.13

vang

-0.13

POSITIVE LOGITS

 actress

0.22

 Actress

0.21

 actor

0.20

 Gene

0.19

 Actor

0.19

Dav

0.19

 celebrity

0.18

 gist

0.18

 Mercy

0.18

 actresses

0.18

Activations Density 0.019%

references to film-related professions and projects

No Comments

No Known Activations