INDEX

Explanations

references to locations and communities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

SSI

-0.17

 ZÃ¡p

-0.15

Metro

-0.15

arium

-0.15

Ø§ØªÛĮ

-0.14

 Metro

-0.14

ICAST

-0.14

itere

-0.14

OPY

-0.13

ì¼ĵ

-0.13

POSITIVE LOGITS

Jew

0.21

 Agency

0.19

 Orient

0.19

 rural

0.19

 Baltic

0.19

Agency

0.18

 Friendship

0.18

 Union

0.18

 Clim

0.18

 Harmony

0.18

Activations Density 0.071%

references to locations and communities

No Comments

No Known Activations