INDEX

Explanations

requests for help or assistance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

.setPrototypeOf

-0.15

Ans

-0.15

sip

-0.14

Ans

-0.14

alach

-0.14

anker

-0.14

enance

-0.14

agree

-0.14

oha

-0.13

ilogy

-0.13

POSITIVE LOGITS

mut

0.15

PGA

0.14

essim

0.14

mekte

0.14

/Area

0.14

oÄŁ

0.14

 ä¿¡

0.14

ÐķÐ¡

0.14

æŃ¦

0.13

andum

0.13

Activations Density 0.176%

requests for help or assistance

No Comments

No Known Activations