INDEX

Explanations

frequency of definite articles and certain nouns, indicating a focus on specific subjects or themes, particularly in formal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.15

aign

-0.15

apis

-0.14

 disparate

-0.14

 denen

-0.14

emsp

-0.14

etail

-0.14

 unwitting

-0.14

 offending

-0.14

 lone

-0.14

POSITIVE LOGITS

ese

0.26

 mentioned

0.25

 hereby

0.23

 nowadays

0.22

 whole

0.21

 Â«

0.20

 âĢŀ

0.19

oric

0.19

pec

0.19

orical

0.18

Activations Density 0.514%

frequency of definite articles and certain nouns, indicating a focus on specific subjects or themes, particularly in formal contexts

No Comments

No Known Activations