INDEX

Explanations

geographical references and location-specific details

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

 beach

-0.18

ssid

-0.15

ivol

-0.15

inidad

-0.15

 Beach

-0.15

?:

-0.15

LEX

-0.14

 cliff

-0.13

orian

-0.13

Î±Î½Î¬

-0.13

POSITIVE LOGITS

 Ever

0.34

Ever

0.27

 ever

0.23

 EVER

0.21

Tam

0.19

-ever

0.18

 sugar

0.17

Mic

0.17

Tam

0.16

 Cork

0.16

Activations Density 0.013%

geographical references and location-specific details

No Comments

No Known Activations