INDEX

Explanations

references to political topics and discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

umer

-0.19

celik

-0.18

ĭ

-0.16

 Warp

-0.15

iciel

-0.15

apesh

-0.15

Î»Î¹Îº

-0.14

Ã³s

-0.14

lder

-0.14

Ð»ÑıÐ´

-0.14

POSITIVE LOGITS

 correctness

0.29

 incorrect

0.27

 Incorrect

0.22

-economic

0.20

incorrect

0.19

 prisoners

0.18

 scientist

0.18

 Correct

0.18

 correct

0.18

 prisoner

0.17

Activations Density 0.016%

references to political topics and discussions

No Comments

No Known Activations