INDEX

Explanations

terms related to restoration and recovery processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

estic

-0.15

irut

-0.15

ye

-0.15

astro

-0.15

OrDefault

-0.15

ADB

-0.14

ãĥ¼ãĥĩ

-0.14

uty

-0.14

ä¸Ķ

-0.14

POSITIVE LOGITS

ments

0.18

ignum

0.17

/rest

0.17

uish

0.16

ellite

0.15

amus

0.15

ment

0.15

¼åĲĪ

0.15

itution

0.15

 Supplies

0.15

Activations Density 0.028%

terms related to restoration and recovery processes

No Comments

No Known Activations