INDEX

Explanations

references to kitchens and kitchen features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

alama

-0.16

ustin

-0.15

/static

-0.15

-0.14

tÃ¼r

-0.14

 FactoryGirl

-0.14

chal

-0.14

ustria

-0.13

uden

-0.13

POSITIVE LOGITS

IGHL

0.20

ete

0.17

lab

0.17

æª

0.16

kontakte

0.15

-mouth

0.15

IGHLIGHT

0.15

etics

0.15

ounty

0.15

burgh

0.15

Activations Density 0.045%

references to kitchens and kitchen features

No Comments

No Known Activations