INDEX

Explanations

references to historical events and significant figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ziej

-0.21

Ùĭ

-0.19

boru

-0.19

parison

-0.18

cape

-0.17

yla

-0.17

arcer

-0.17

kiye

-0.16

-thirds

-0.16

rollo

-0.16

POSITIVE LOGITS

ate

0.35

ine

0.34

ian

0.34

ous

0.33

ic

0.33

ens

0.33

ie

0.33

ies

0.33

ern

0.33

us

0.32

Activations Density 1.828%

references to historical events and significant figures

No Comments

No Known Activations