INDEX

Explanations

names and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 jadx

-0.16

BERT

-0.15

 AppConfig

-0.15

esti

-0.15

 Walsh

-0.14

adol

-0.14

 ingest

-0.13

 Cypress

-0.13

Bak

-0.13

 CORS

-0.13

POSITIVE LOGITS

hyp

0.23

Guest

0.22

 Guest

0.21

 guest

0.20

guest

0.20

hyp

0.20

kvm

0.20

 Image

0.20

 pool

0.20

Pool

0.20

Activations Density 0.007%

names and identifiers

No Comments

No Known Activations