INDEX

Explanations

terminology 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 @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

agos

-0.16

__()

-0.15

rench

-0.14

Î³Î®

-0.14

ollo

-0.14

ãĥ¼ãĥĦ

-0.14

posables

-0.14

btn

-0.14

essen

-0.14

onto

-0.13

POSITIVE LOGITS

ar

0.17

ad

0.16

 among

0.15

 caused

0.15

can

0.15

bjerg

0.14

 usually

0.14

 brand

0.14

 ÑĢÐ¸Ð·

0.14

Activations Density 0.090%

terminology related to mental health disorders and their symptoms

No Comments

No Known Activations

terminology related to mental health disorders and their symptoms

No Comments

No Known Activations