INDEX

Explanations

terms and phrases related to medical and health-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

unei

-0.15

erland

-0.14

ucene

-0.14

 Moff

-0.14

ninger

-0.14

ouver

-0.14

ANCELED

-0.14

Jab

-0.14

udeau

-0.14

POSITIVE LOGITS

 bdsm

0.17

cus

0.16

 Rosen

0.15

ira

0.14

iec

0.14

rey

0.14

.gf

0.14

modifiable

0.14

ears

0.13

redd

0.13

Activations Density 0.497%

terms and phrases related to medical and health-related topics

No Comments

No Known Activations