INDEX

Explanations

references to events happening in the past

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

embro

-0.15

ÄŁan

-0.15

Ð¾Ð·Ð²ÑĢÐ°Ñī

-0.14

dependent

-0.14

adays

-0.14

ctest

-0.13

akening

-0.13

 nouve

-0.13

 ÑģÐ¾ÑĢ

-0.13

fonts

-0.13

POSITIVE LOGITS

 Chance

0.27

ing

0.27

 modified

0.26

 Modified

0.26

 edited

0.23

 Updated

0.23

 chance

0.23

 updated

0.22

Chance

0.22

 year

0.21

Activations Density 0.016%

references to events happening in the past

No Comments

No Known Activations