INDEX

Explanations

terms related to health and disease prevention

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

andest

-0.22

orda

-0.16

ozem

-0.15

 limburg

-0.15

riz

-0.14

elage

-0.14

SCII

-0.14

pressor

-0.14

 link

-0.14

 láº¡c

-0.14

POSITIVE LOGITS

-ins

0.30

Ins

0.28

Ins

0.28

ins

0.27

INS

0.24

INS

0.23

_ins

0.23

 Turn

0.22

(ins

0.22

(turn

0.21

Activations Density 0.027%

terms related to health and disease prevention

No Comments

No Known Activations