INDEX

Explanations

references to World War I and World War II

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ities

-0.17

ctl

-0.17

ife

-0.15

apture

-0.15

 Victorian

-0.14

 older

-0.14

ilar

-0.14

Ø³ÙĬÙĨ

-0.14

etti

-0.14

 Downing

-0.14

POSITIVE LOGITS

-era

0.33

era

0.26

era

0.24

Era

0.22

ERA

0.18

-period

0.17

 dÃ¶nemde

0.17

å½¹

0.17

ucene

0.16

hamster

0.16

Activations Density 0.032%

references to World War I and World War II

No Comments

No Known Activations