INDEX

Explanations

positive descriptors related to experiences and people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

oko

-0.16

ifiable

-0.16

.lv

-0.15

ä¼į

-0.15

elem

-0.15

 favorites

-0.14

enville

-0.14

ounder

-0.14

olvers

-0.14

POSITIVE LOGITS

lest

0.28

-grand

0.22

mente

0.21

ness

0.20

-looking

0.17

ment

0.17

ous

0.16

iterals

0.16

ously

0.16

ly

0.16

Activations Density 0.043%

positive descriptors related to experiences and people

No Comments

No Known Activations