INDEX

Explanations

phrases and sentences that indicate supplementation or reference articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

_finalize

-0.16

tÃ¼

-0.15

reich

-0.15

 sketch

-0.14

ker

-0.14

 Karn

-0.14

ãĥ³ãĥĲ

-0.13

ilda

-0.13

Éµ

-0.13

á»Ļ

-0.13

POSITIVE LOGITS

RELATED

0.28

READ

0.27

 RELATED

0.27

 read

0.26

 READ

0.26

 Related

0.26

SEE

0.23

Related

0.22

imson

0.20

read

0.20

Activations Density 0.085%

phrases and sentences that indicate supplementation or reference articles

No Comments

No Known Activations