INDEX

Explanations

keywords related to cataloging or listing in a specified context

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

ihan

-0.15

vection

-0.14

.tar

-0.14

aba

-0.14

 Economist

-0.13

zano

-0.13

lane

-0.13

olars

-0.13

 Kostenlos

-0.13

Ä±y

-0.13

POSITIVE LOGITS

arter

0.17

placer

0.16

ameda

0.16

acking

0.15

vos

0.14

licit

0.14

 prelim

0.14

lista

0.14

 present

0.14

 list

0.14

Activations Density 0.005%

keywords related to cataloging or listing in a specified context

No Comments

No Known Activations