INDEX

Explanations

prefixes and suffixes related to scientific terminology and classification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

QUIRES

-0.19

tures

-0.16

encies

-0.15

Eag

-0.15

eldorf

-0.15

ÅĽÄĩ

-0.14

Ã§Ãµes

-0.14

arily

-0.14

keit

-0.14

Jug

-0.14

POSITIVE LOGITS

ulous

0.17

ulent

0.14

bye

0.14

ground

0.14

usb

0.14

at

0.13

nature

0.13

 Ã¼nlÃ¼

0.13

lucent

0.13

orious

0.13

Activations Density 0.187%

prefixes and suffixes related to scientific terminology and classification

No Comments

No Known Activations