INDEX

Explanations

terms related to well-being and 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 @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Ã¼ss

-0.19

imei

-0.17

abez

-0.16

avez

-0.15

elect

-0.14

ÛĮØ§ÙĨ

-0.14

ukt

-0.14

cess

-0.14

amedi

-0.14

dÄ±r

-0.13

POSITIVE LOGITS

athers

0.18

Mig

0.17

ows

0.16

inder

0.16

readcr

0.15

trys

0.15

ington

0.15

uard

0.14

olec

0.14

Rnd

0.14

Activations Density 0.015%

terms related to well-being and mental health

No Comments

No Known Activations