INDEX

Explanations

connections and relationships among concepts, particularly regarding artistic and environmental contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ÏĥÏĦÎµ

-0.17

ewriter

-0.17

eres

-0.15

ymoon

-0.15

ircular

-0.14

ÑĮÐµ

-0.14

 thá»ķ

-0.14

Ã©gor

-0.14

msp

-0.14

EDI

-0.14

POSITIVE LOGITS

us

0.20

rai

0.20

ues

0.20

ait

0.18

cus

0.18

ons

0.18

ant

0.18

rait

0.17

ÌĤ

0.17

Activations Density 0.019%

connections and relationships among concepts, particularly regarding artistic and environmental contexts

No Comments

No Known Activations