INDEX

Explanations

phrases related to actions involving managing or processing data and tasks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ingle

-0.16

MD

-0.15

ATO

-0.15

omon

-0.15

ÄĻÅ¼

-0.14

iper

-0.14

enson

-0.14

assi

-0.14

INGLE

-0.14

hole

-0.14

POSITIVE LOGITS

issen

0.16

 swingers

0.15

iche

0.15

 Sender

0.15

eer

0.14

andest

0.14

utton

0.14

rides

0.14

 turno

0.14

Activations Density 0.208%

phrases related to actions involving managing or processing data and tasks

No Comments

No Known Activations