INDEX

Explanations

data type declarations and memory management-related terms

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

esch

-0.16

Seed

-0.15

 Seed

-0.14

enthal

-0.14

èķī

-0.14

lad

-0.14

 down

-0.14

 tail

-0.14

alyze

-0.14

POSITIVE LOGITS

 Sche

0.17

.gdx

0.15

 taraf

0.15

æħ§

0.14

.digest

0.14

alÄ±k

0.14

ulings

0.14

uben

0.13

apters

0.13

oll

0.13

Activations Density 0.023%

data type declarations and memory management-related terms

No Comments

No Known Activations