INDEX

Explanations

references to significant time periods and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ibel

-0.17

ogne

-0.17

elopment

-0.17

arna

-0.16

Ð¾Ð·Ð½Ð°

-0.15

ä¸Ģä¸ĭ

-0.14

ë¦¬ì¹´

-0.14

indre

-0.14

 ì²«

-0.14

azen

-0.14

POSITIVE LOGITS

 ever

0.35

-ever

0.34

 EVER

0.28

ever

0.25

 since

0.24

 anywhere

0.20

Ever

0.19

 nÃło

0.19

EVER

0.19

 Ever

0.19

Activations Density 0.020%

references to significant time periods and events

No Comments

No Known Activations