INDEX

Explanations

titles and noteworthy phrases associated with popular culture and societal issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

çĭĲ

-0.14

oday

-0.14

vais

-0.13

ØºØ§ÙĦ

-0.13

fans

-0.13

uest

-0.13

Ã³c

-0.13

 åĪ¶

-0.13

åĪ¶

-0.13

_GPIO

-0.13

POSITIVE LOGITS

 syndrome

0.20

 dreaded

0.19

 phenomenon

0.18

‘

0.18

 Syndrome

0.16

0.15

gate

0.15

Ãĭ

0.14

Named

0.14

“

0.14

Activations Density 0.288%

titles and noteworthy phrases associated with popular culture and societal issues

No Comments

No Known Activations