INDEX

Explanations

concepts and research related to psychiatric illness and cognitive assessment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

dct

-0.15

aign

-0.15

QUI

-0.14

 wound

-0.14

LRV

-0.14

ä¸Ī

-0.14

coli

-0.13

 disag

-0.13

nap

-0.13

POSITIVE LOGITS

 Circuit

0.21

 circuit

0.20

 measures

0.20

 reward

0.19

 regions

0.19

/exec

0.19

 executive

0.19

 Measures

0.18

insula

0.18

Region

0.18

Activations Density 0.039%

concepts and research related to psychiatric illness and cognitive assessment

No Comments

No Known Activations