INDEX

Explanations

roles or titles associated with individuals in various professions or activities

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

 another

-0.19

our

-0.18

 their

-0.17

 hoáº·c

-0.17

æĪĸ

-0.17

æĪĸèĢħ

-0.16

 EITHER

-0.16

 either

-0.16

 Ð°Ð±Ð¾

-0.16

POSITIVE LOGITS

-turned

0.43

 extra

0.41

 turned

0.38

-extra

0.38

extra

0.34

0.32

 extraordin

0.31

turned

0.29

 Extra

0.28

and

0.28

Activations Density 0.181%

roles or titles associated with individuals in various professions or activities

No Comments

No Known Activations