INDEX

Explanations

health and wellness terms, specifically focusing on ingredients or components in food and medicine

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 aliqua

-0.16

 Tarif

-0.15

gregar

-0.14

gree

-0.14

ë¦¬ìĬ¤

-0.14

 Erotik

-0.14

verty

-0.13

ideo

-0.13

uments

-0.13

gre

-0.13

POSITIVE LOGITS

istik

0.15

lh

0.14

combination

0.14

Ã¼re

0.14

 âĢ¦

0.14

ä»Ģ

0.13

 circ

0.13

TURE

0.12

Sir

0.12

osoph

0.12

Activations Density 0.201%

health and wellness terms, specifically focusing on ingredients or components in food and medicine

No Comments

No Known Activations