INDEX

Explanations

phrases involving comprehensive coverage or evaluation of subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

aln

-0.15

ÏĥÏį

-0.15

rette

-0.15

edImage

-0.15

 EntityState

-0.14

Ð³Ð¾ÑĤ

-0.14

Ø®Ø§ÙĨ

-0.14

ursively

-0.13

LayoutManager

-0.13

oric

-0.13

POSITIVE LOGITS

 aspects

0.73

 aspect

0.71

aspect

0.62

 facets

0.61

 Aspect

0.56

Aspect

0.52

 facet

0.50

 dimensions

0.48

pects

0.46

æĸ¹éĿ¢

0.43

Activations Density 0.212%

phrases involving comprehensive coverage or evaluation of subjects

No Comments

No Known Activations