INDEX

Explanations

references to recent events or developments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

emes

-0.17

iard

-0.16

slaught

-0.15

ÑģÐ¿ÑĸÐ»ÑĮ

-0.14

ÐºÐ¾ÑĢ

-0.14

shots

-0.14

\<^

-0.13

 Princip

-0.13

Ð½Ð¸Ñĩ

-0.13

POSITIVE LOGITS

 times

0.41

 memory

0.38

 years

0.37

 months

0.30

memory

0.28

 history

0.28

 decades

0.27

 MEMORY

0.26

 Memory

0.26

times

0.25

Activations Density 0.015%

references to recent events or developments

No Comments

No Known Activations