INDEX

Explanations

specific product features and indicators related to discussions of consumer goods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

bei

-0.16

Î´Î±

-0.15

pard

-0.14

aux

-0.14

cke

-0.14

 bÄĻd

-0.14

ovah

-0.13

bridge

-0.13

pyx

-0.13

POSITIVE LOGITS

 Raid

0.15

.spi

0.14

asic

0.14

Rus

0.14

UNCH

0.14

Zuk

0.14

 Peer

0.13

asma

0.13

_builder

0.13

Mob

0.13

Activations Density 0.361%

specific product features and indicators related to discussions of consumer goods

No Comments

No Known Activations