INDEX

Explanations

mentions of various professionals and their associated institutions or roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

âĢĮØ¯Ùĩ

-0.14

aters

-0.14

 heads

-0.14

ervo

-0.14

wk

-0.14

ependency

-0.13

Copyright

-0.13

ories

-0.13

desktop

-0.13

POSITIVE LOGITS

 unnamed

0.22

 local

0.19

åı«

0.19

 obscure

0.19

 private

0.18

 undisclosed

0.17

 nearby

0.16

 prominent

0.16

 couple

0.16

 group

0.16

Activations Density 0.284%

mentions of various professionals and their associated institutions or roles

No Comments

No Known Activations