INDEX

Explanations

numerical ranges and comparative quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

pras

-0.17

usz

-0.16

ONGO

-0.16

anzeigen

-0.16

ught

-0.16

NTN

-0.16

.EntityManager

-0.16

nÄĽji

-0.15

ppe

-0.15

ili

-0.15

POSITIVE LOGITS

 minimum

0.28

 Minimum

0.23

minimum

0.20

Minimum

0.20

 single

0.18

 zero

0.18

 legal

0.17

 smallest

0.17

cr

0.16

 absolute

0.15

Activations Density 0.096%

numerical ranges and comparative quantities

No Comments

No Known Activations