INDEX

Explanations

references to health-related topics and organizational roles within health campaigns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

fiber

-0.18

 afterward

-0.17

 behaviors

-0.17

Behavior

-0.17

 Drone

-0.16

 drones

-0.16

behavior

-0.16

 playbook

-0.16

 Narr

-0.15

 fiber

-0.15

POSITIVE LOGITS

 consultancy

0.20

 generic

0.17

kills

0.17

 modem

0.16

 consult

0.16

 activity

0.16

 flair

0.16

 programmes

0.16

 inputs

0.16

 worthwhile

0.16

Activations Density 0.384%

references to health-related topics and organizational roles within health campaigns

No Comments

No Known Activations