INDEX

Explanations

expressions related to user experiences and operational insights

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ilha

-0.16

arde

-0.16

ë¦¿

-0.16

-0.15

rief

-0.15

 Northern

-0.15

.hh

-0.15

-0.14

POSITIVE LOGITS

rat

0.17

IOC

0.15

opt

0.15

anium

0.15

/inet

0.15

onomous

0.15

 rescue

0.14

 resc

0.14

 opted

0.14

ableObject

0.14

Activations Density 0.030%

expressions related to user experiences and operational insights

No Comments

No Known Activations