INDEX

Explanations

terms related to service-oriented concepts and frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

Services

-0.21

ervices

-0.20

 Services

-0.18

 services

-0.18

services

-0.17

 SERVICES

-0.16

wort

-0.16

ÑĥÑĪÐºÐ¸

-0.16

ences

-0.15

ervers

-0.15

POSITIVE LOGITS

able

0.27

ability

0.26

berry

0.20

-learning

0.20

ABLE

0.19

ably

0.17

 learning

0.17

learning

0.17

achi

0.16

CEE

0.16

Activations Density 0.024%

terms related to service-oriented concepts and frameworks

No Comments

No Known Activations