INDEX

Explanations

phrases related to mental health support and referrals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

nete

-0.16

ìĬ¤íĬ¸

-0.14

ÑĨÐµÐ²

-0.14

 Undo

-0.14

tul

-0.14

rip

-0.13

wipe

-0.13

axter

-0.13

ä»ĺ

-0.13

 programmes

-0.13

POSITIVE LOGITS

tri

0.20

tri

0.17

 assessment

0.16

 Assessment

0.16

 Teams

0.15

 assessments

0.15

holm

0.14

 teams

0.14

esk

0.14

 suspected

0.14

Activations Density 0.012%

phrases related to mental health support and referrals

No Comments

No Known Activations