INDEX

Explanations

prominent names and titles in various contexts, often associated with artistic or influential individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Ãºn

-0.16

arlo

-0.14

 Benson

-0.14

Ã¼st

-0.14

.enterprise

-0.13

opsis

-0.13

agu

-0.13

(EXPR

-0.13

vention

-0.13

oire

-0.13

POSITIVE LOGITS

 himself

0.23

 ÙĨÙģØ³Ùĩ

0.21

Jr

0.20

 Himself

0.16

nesty

0.15

åįļå£«

0.15

##_

0.14

III

0.14

åħĪçĶŁ

0.14

çĪµ

0.14

Activations Density 0.077%

prominent names and titles in various contexts, often associated with artistic or influential individuals

No Comments

No Known Activations