INDEX

Explanations

references to military ranks and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

icus

-0.19

åĢĴ

-0.16

Ð¾ÑĢÐ°Ñı

-0.15

 addCriterion

-0.15

andin

-0.14

à¸«à¸¡à¸²à¸¢

-0.14

ä»

-0.14

ë§¹

-0.14

ulario

-0.14

åĲįçĦ¡ãģĹ

-0.14

POSITIVE LOGITS

-Col

0.30

 colon

0.28

 Colonel

0.27

-col

0.25

colon

0.24

-General

0.23

Colon

0.22

 governor

0.22

 Governor

0.22

eneral

0.21

Activations Density 0.011%

references to military ranks and titles

No Comments

No Known Activations