INDEX

Explanations

references to safety and compliance within regulated environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

-0.16

anske

-0.16

usto

-0.15

wert

-0.15

logan

-0.14

Applied

-0.14

.metro

-0.14

 stan

-0.13

oley

-0.13

 Applied

-0.13

POSITIVE LOGITS

 drug

0.24

 Drug

0.22

 Drugs

0.20

 drugs

0.20

 medicines

0.19

 medicinal

0.18

drug

0.18

 pharmac

0.18

 dossier

0.18

Drug

0.17

Activations Density 0.023%

references to safety and compliance within regulated environments

No Comments

No Known Activations