INDEX

Explanations

mentions of software

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

uate

-0.15

Ale

-0.14

onym

-0.14

ore

-0.14

<decltype

-0.14

Ð¾Ð²Ð¸

-0.14

oto

-0.14

 PROGMEM

-0.13

Arm

-0.13

eldo

-0.13

POSITIVE LOGITS

ething

0.18

\Carbon

0.15

villa

0.15

âĶĶ

0.15

Î¸Î±

0.14

>NN

0.14

------+------+

0.14

 dilig

0.14

ichen

0.14

>manual

0.13

Activations Density 0.013%

mentions of software

No Comments

No Known Activations