INDEX

Explanations

adverbs that indicate certainty, frequency, or degree of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

-0.20

ses

-0.16

åħ¶å®ŀ

-0.14

/or

-0.14

 Ð½Ð°Ð¿ÑĢÐ¸

-0.13

’d

-0.13

'd

-0.13

ï

-0.13

’ll

-0.13

 realmente

-0.13

POSITIVE LOGITS

mente

0.24

jÅ¡ÃŃ

0.21

(?)

0.21

-ÑĤÐ°ÐºÐ¸

0.20

forth

0.20

LY

0.19

most

0.18

Ùĭ

0.18

ifiable

0.17

aneously

0.17

Activations Density 0.596%

adverbs that indicate certainty, frequency, or degree of something

No Comments

No Known Activations