INDEX

Explanations

terms related to emotional and psychological well-being, including symptoms of mental disorders

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

erna

-0.16

enville

-0.16

lemen

-0.15

 âĹĦ

-0.15

oppers

-0.15

aca

-0.15

isz

-0.15

Ä¢

-0.15

ocrats

-0.15

/Private

-0.14

POSITIVE LOGITS

 functioning

0.28

 status

0.25

status

0.22

 scores

0.20

 statuses

0.19

 Status

0.19

_status

0.19

 function

0.18

.status

0.18

 outcome

0.18

Activations Density 0.131%

terms related to emotional and psychological well-being, including symptoms of mental disorders

No Comments

No Known Activations