INDEX

Explanations

references to experimental results and their significance

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

.scalablytyped

-0.22

chluss

-0.17

ammer

-0.15

esson

-0.15

ncia

-0.15

ijkl

-0.14

 lucr

-0.14

ãĥ³ãĥĹ

-0.14

imus

-0.14

ä¸įè¶³

-0.14

POSITIVE LOGITS

 performance

0.35

performance

0.28

 Performance

0.27

 performances

0.25

Performance

0.25

æĢ§èĥ½

0.23

 PERFORMANCE

0.23

 accuracy

0.21

 improvement

0.21

.performance

0.21

Activations Density 0.049%

references to experimental results and their significance

No Comments

No Known Activations