INDEX

Explanations

common phrases and terms associated with comparison and contrast

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ediator

-0.15

teÅŁ

-0.15

ibold

-0.15

æĦıæĢĿ

-0.14

jvu

-0.14

Authority

-0.14

acades

-0.14

éģ£

-0.14

Wunused

-0.13

Ĩ

-0.13

POSITIVE LOGITS

 popular

0.28

 famous

0.25

 infamous

0.24

popular

0.24

 much

0.24

 legendary

0.21

 well

0.21

Popular

0.20

 once

0.20

 Famous

0.20

Activations Density 0.095%

common phrases and terms associated with comparison and contrast

No Comments

No Known Activations