INDEX

Explanations

terms related to depression and mental health issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 Verde

-0.17

recision

-0.15

 Cald

-0.14

mie

-0.14

onet

-0.14

liness

-0.14

etcode

-0.14

flux

-0.14

relude

-0.14

å¨ģ

-0.13

POSITIVE LOGITS

 depression

0.22

 Depression

0.21

/an

0.20

 depressive

0.20

 mood

0.18

 melanch

0.18

 depressed

0.17

Dep

0.17

Sad

0.16

sad

0.16

Activations Density 0.018%

terms related to depression and mental health issues

No Comments

No Known Activations