INDEX

Explanations

references to specific locations and names associated with art, culture, and history

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

 Appalach

-0.16

 Yellowstone

-0.14

umberland

-0.14

 Highlands

-0.14

western

-0.13

leigh

-0.13

 Cumberland

-0.13

 MSNBC

-0.13

 Erie

-0.13

 Asheville

-0.13

POSITIVE LOGITS

jr

0.28

 alias

0.27

 junior

0.25

(*

0.23

 Junior

0.21

ovÃ¡

0.20

-Za

0.19

und

0.18

 himself

0.18

 senior

0.18

Activations Density 0.150%

references to specific locations and names associated with art, culture, and history

No Comments

No Known Activations