INDEX

Explanations

references to historical architecture and notable structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

uat

-0.17

ussy

-0.15

adia

-0.15

uelle

-0.14

azzo

-0.14

Ã©ra

-0.14

 partial

-0.14

sess

-0.14

ereo

-0.14

.scalablytyped

-0.14

POSITIVE LOGITS

-e

0.31

-i

0.23

Rud

0.22

 Tape

0.19

 Ð¾ÑģÑĤÐ°Ð½

0.16

Gon

0.16

âĢĮØ§ÙĨØ¨Ø§Ø±

0.16

veh

0.15

Pir

0.15

ÑĢÑĥÐ´

0.15

Activations Density 0.045%

references to historical architecture and notable structures

No Comments

No Known Activations