INDEX

Explanations

references to specific individuals and their professional roles

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

oldem

-0.17

abric

-0.16

uin

-0.15

 Ø¹ÙĤ

-0.15

uffs

-0.14

ãĥ¼ãĤ¹

-0.14

embro

-0.14

ENU

-0.14

UL

-0.14

åľ¨çº¿è§Ĥçľĭ

-0.14

POSITIVE LOGITS

 inter

0.27

 next

0.26

 Inter

0.23

inter

0.21

 stations

0.20

 station

0.20

NEXT

0.20

next

0.20

Inter

0.19

 Station

0.19

Activations Density 0.009%

references to specific individuals and their professional roles

No Comments

No Known Activations