INDEX

Explanations

scientific terminology and references related to experimental results and comparisons

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

.scalablytyped

-0.19

ãĤ¤ãĥī

-0.15

lew

-0.14

koli

-0.14

æ°ı

-0.14

AMAGE

-0.14

å£«

-0.14

ãĥ³ãĥĹ

-0.13

bis

-0.13

POSITIVE LOGITS

 performance

0.34

performance

0.28

 performances

0.28

 accuracy

0.27

Performance

0.26

 Performance

0.26

æĢ§èĥ½

0.26

 competitive

0.24

 Accuracy

0.24

 accur

0.23

Activations Density 0.063%

scientific terminology and references related to experimental results and comparisons

No Comments

No Known Activations