INDEX

Explanations

specific numbers and their representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

onic

-0.18

lk

-0.15

iro

-0.15

olest

-0.15

-prop

-0.14

uler

-0.14

abby

-0.14

olid

-0.14

prd

-0.14

POSITIVE LOGITS

.scalablytyped

0.18

omik

0.16

con

0.15

DDD

0.14

 Relatives

0.14

AlmostEqual

0.14

Conclusion

0.14

ãĤ¦ãĥĪ

0.13

="../../../

0.13

 UICollectionViewCell

0.13

Activations Density 0.002%

specific numbers and their representations

No Comments

No Known Activations