INDEX

Explanations

references to military conflict and strategies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

.Serve

-0.15

pective

-0.15

ÎµÎ¹Î¿

-0.15

thouse

-0.14

¡´

-0.14

èĴ

-0.14

CLS

-0.14

esto

-0.14

abwe

-0.14

-bars

-0.13

POSITIVE LOGITS

 Berger

0.18

0.17

Ø²Ø§Ø±

0.15

inalg

0.15

ablish

0.15

.GetItem

0.14

Geh

0.14

Ø²Ø§ÙĨ

0.14

atten

0.14

uess

0.14

Activations Density 0.169%

references to military conflict and strategies

No Comments

No Known Activations