INDEX

Explanations

terms related to mental health disorders and their symptoms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 sick

-0.17

lish

-0.15

èľ

-0.15

omm

-0.15

íĻľ

-0.15

@student

-0.15

submenu

-0.15

itsu

-0.15

VD

-0.14

 ÑģÑĢÐ¾Ðº

-0.14

POSITIVE LOGITS

 Sach

0.17

han

0.15

Î»Î¹

0.15

rak

0.14

 Orchard

0.14

 Schro

0.14

ì²ľ

0.14

atre

0.13

 Besch

0.13

Activations Density 0.044%

terms related to mental health disorders and their symptoms

No Comments

No Known Activations