INDEX

Explanations

references to medications and their effects related to mental health

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

hausen

-0.19

å¸

-0.14

oftware

-0.14

Ð³Ð¾Ð²

-0.14

Ha

-0.14

è¾°

-0.14

ccak

-0.14

uga

-0.14

dna

-0.13

 Arthropoda

-0.13

POSITIVE LOGITS

SSR

0.36

 antidepress

0.36

SS

0.35

 serotonin

0.33

ser

0.31

Ser

0.30

oxetine

0.29

SS

0.28

idepress

0.27

ss

0.26

Activations Density 0.067%

references to medications and their effects related to mental health

No Comments

No Known Activations