INDEX

Explanations

phrases related to personal health and well-being

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

roke

-0.15

 stuff

-0.15

opic

-0.15

 dragons

-0.14

cka

-0.14

aura

-0.14

stuff

-0.14

isphere

-0.13

 Mutual

-0.13

Ã¢m

-0.13

POSITIVE LOGITS

or

0.21

0.18

ï¼ĮæĪĸ

0.16

 oder

0.16

ebb

0.16

mpz

0.16

nor

0.15

 Ð¸Ð»Ð¸

0.15

ê±°ëĤĺ

0.15

 æĪĸ

0.15

Activations Density 0.046%

phrases related to personal health and well-being

No Comments

No Known Activations