INDEX

Explanations

references to the concept of norms and their implications in society

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 entirety

-0.25

 entire

-0.25

 whole

-0.20

whole

-0.18

 possibility

-0.18

 Entire

-0.18

 presence

-0.18

 chance

-0.16

 opportunity

-0.16

 equivalent

-0.15

POSITIVE LOGITS

 early

0.19

 earlier

0.18

 newer

0.18

 recent

0.17

 earliest

0.16

 major

0.16

 many

0.16

 later

0.16

oldem

0.15

many

0.15

Activations Density 0.138%

references to the concept of norms and their implications in society

No Comments

No Known Activations