INDEX

Explanations

terms related to degeneration and degenerative conditions

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

eru

-0.18

anden

-0.15

ebb

-0.15

vely

-0.15

oft

-0.15

ics

-0.15

 NavParams

-0.14

er

-0.14

phere

-0.14

 gilt

-0.14

POSITIVE LOGITS

deg

0.24

enerative

0.24

enerate

0.23

-rad

0.21

ener

0.21

rad

0.20

Deg

0.20

enerated

0.20

eneration

0.18

Deg

0.18

Activations Density 0.006%

terms related to degeneration and degenerative conditions

No Comments

No Known Activations