INDEX

Explanations

mentions of films and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

zw

-0.17

ecurity

-0.16

embre

-0.15

 Abed

-0.15

.Toolkit

-0.15

Ð¾ÐºÑĢÐµÐ¼

-0.15

 triang

-0.14

Ã¡b

-0.14

haul

-0.14

.lesson

-0.14

POSITIVE LOGITS

Tel

0.23

 hero

0.22

tol

0.22

 heroine

0.21

 mass

0.20

 keer

0.20

 Mega

0.20

tel

0.20

 interval

0.20

 Hero

0.20

Activations Density 0.011%

mentions of films and their attributes

No Comments

No Known Activations