INDEX

Explanations

discussions about mental 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 @ 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

client

-0.16

 Yelp

-0.15

clients

-0.15

avior

-0.15

 client

-0.15

ettel

-0.14

ComputedStyle

-0.14

 clients

-0.13

 Vict

-0.13

_intr

-0.13

POSITIVE LOGITS

 mental

0.43

 Mental

0.41

mental

0.36

 mentally

0.28

 suicide

0.26

MENT

0.25

MH

0.24

 Samar

0.23

 Mind

0.22

 Ment

0.22

Activations Density 0.043%

discussions about mental health and well-being

No Comments

No Known Activations