INDEX

Explanations

specific characters and symbols used in programming syntax and formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

dee

-0.16

adin

-0.15

imitive

-0.14

wi

-0.14

spi

-0.14

éĻ£

-0.13

adesh

-0.13

kak

-0.13

 trainable

-0.13

;amp

-0.13

POSITIVE LOGITS

0.20

igos

0.19

yk

0.18

 gratuiti

0.15

Ã©ra

0.15

Pav

0.15

yr

0.14

 Joyce

0.14

Tin

0.14

vyk

0.14

Activations Density 0.170%

specific characters and symbols used in programming syntax and formatting

No Comments

No Known Activations