INDEX

Explanations

references to historical events and acts of violence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

furt

-0.17

é¼»

-0.16

aliz

-0.15

vard

-0.15

.AddParameter

-0.15

 Ð³Ð¾ÑģÐ¿

-0.14

Å¾i

-0.14

dej

-0.14

azing

-0.13

orne

-0.13

POSITIVE LOGITS

 resistance

0.28

Resistance

0.26

 Resistance

0.26

 Resist

0.24

 resist

0.23

 independence

0.23

 freedom

0.22

 Independence

0.21

 ÙħÙĤØ§ÙĪ

0.20

 khÃ¡ng

0.20

Activations Density 0.233%

references to historical events and acts of violence

No Comments

No Known Activations