INDEX

Explanations

metrics related to performance and success

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

but

-0.61

but

-0.49

 nhÆ°ng

-0.45

 Ð½Ð¾

-0.41

ï¼Įä½Ĩ

-0.40

 maar

-0.39

 pero

-0.38

ä½Ĩ

-0.38

ãģłãģĮ

-0.37

_but

-0.36

POSITIVE LOGITS

 nonetheless

0.21

 nevertheless

0.17

izo

0.16

 elsewhere

0.15

ãģ®æĸ¹

0.15

itive

0.15

 Ultimately

0.14

ulta

0.14

 Otherwise

0.13

otherwise

0.13

Activations Density 0.679%

metrics related to performance and success

No Comments

No Known Activations