INDEX

Explanations

organizational affiliations and geographic locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ynet

-0.14

.adv

-0.14

assel

-0.13

occupied

-0.13

elik

-0.13

agher

-0.13

afone

-0.13

è´¹

-0.13

mlin

-0.13

POSITIVE LOGITS

 based

0.94

based

0.83

 Based

0.80

Based

0.76

_based

0.68

 headquartered

0.60

åŁºäºİ

0.55

-based

0.54

 dá»±a

0.50

 located

0.47

Activations Density 0.258%

organizational affiliations and geographic locations

No Comments

No Known Activations