INDEX

Explanations

terms related to medical treatment and energy flow systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

Ã¸y

-0.15

TOTYPE

-0.14

kin

-0.14

oons

-0.14

 Ð©

-0.14

ukan

-0.14

 erotische

-0.14

 Hopkins

-0.13

Ð°ÑĩÐµ

-0.13

Ã¡ce

-0.13

POSITIVE LOGITS

.BLL

0.18

.gov

0.15

 chief

0.15

0.14

seau

0.14

setWidth

0.13

anova

0.13

edImage

0.13

á»Ļc

0.13

olen

0.12

Activations Density 0.180%

terms related to medical treatment and energy flow systems

No Comments

No Known Activations