INDEX

Explanations

key actions related to launching, announcing, and creating initiatives or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

any

-0.20

 someone

-0.20

someone

-0.18

 somebody

-0.18

 either

-0.18

 previous

-0.17

 Someone

-0.16

éĤ£äºĽ

-0.15

ccione

-0.15

antz

-0.15

POSITIVE LOGITS

 what

0.23

what

0.19

 unprecedented

0.18

 another

0.18

 whats

0.18

äºĨä¸Ģ

0.18

 perhaps

0.18

another

0.17

 arguably

0.17

two

0.15

Activations Density 0.260%

key actions related to launching, announcing, and creating initiatives or products

No Comments

No Known Activations