INDEX

Explanations

concepts related to algorithms and their application within systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

antz

-0.16

Wi

-0.15

lap

-0.15

inou

-0.14

ounter

-0.14

_rd

-0.14

 Tradable

-0.14

Cla

-0.14

inton

-0.13

ishi

-0.13

POSITIVE LOGITS

0.15

è²¡

0.14

noinspection

0.14

isen

0.14

 Affero

0.14

ises

0.13

Nir

0.13

 only

0.13

 Each

0.13

Activations Density 0.092%

concepts related to algorithms and their application within systems

No Comments

No Known Activations

concepts related to algorithms and their application within systems

No Comments

No Known Activations