INDEX

Explanations

copyright and licensing terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ÑĮ

-0.17

 Ø±Ø³

-0.16

stup

-0.15

eft

-0.14

.cfg

-0.14

akedirs

-0.13

 plates

-0.13

 Lump

-0.13

 polic

-0.13

/welcome

-0.13

POSITIVE LOGITS

orman

0.17

ubu

0.17

0.16

noch

0.15

peater

0.15

ober

0.14

olen

0.14

ÑĢÐ°Ð²Ð°

0.14

æĿ¡

0.13

kea

0.13

Activations Density 0.008%

copyright and licensing terms

No Comments

No Known Activations