INDEX

Explanations

adverbs that express certainty or emphasize points

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

/or

-0.15

à¸±à¸Ļà¸Ķ

-0.14

ote

-0.14

rut

-0.13

 bÃ½t

-0.13

ãģ¨ãĤĤ

-0.13

 Ã¼z

-0.13

 heraus

-0.13

Ø§Øµ

-0.13

’d

-0.12

POSITIVE LOGITS

 gonna

0.25

 supposed

0.21

forth

0.21

 able

0.19

going

0.18

 meant

0.17

 worth

0.16

 going

0.16

jÅ¡ÃŃ

0.16

-ÑĤÐ°ÐºÐ¸

0.15

Activations Density 0.342%

adverbs that express certainty or emphasize points

No Comments

No Known Activations