INDEX

Explanations

references to research findings and studies related to health and medical issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

omain

-0.18

 elsewhere

-0.16

 altri

-0.14

apr

-0.13

acci

-0.13

Ľå»º

-0.13

é»

-0.13

åľ°ä¸ĭ

-0.12

(org

-0.12

 Pers

-0.12

POSITIVE LOGITS

 exposure

0.19

 certain

0.17

 Exposure

0.16

 among

0.14

 presence

0.14

ä¸ģ

0.14

olio

0.14

 contrary

0.14

 ripple

0.14

 Presence

0.14

Activations Density 0.166%

references to research findings and studies related to health and medical issues

No Comments

No Known Activations