INDEX

Explanations

phrases indicating methods or ways of working and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

udies

-0.17

uD

-0.15

udit

-0.15

 efforts

-0.15

issing

-0.15

 ability

-0.15

uhl

-0.15

-duty

-0.15

 uÄŁ

-0.14

 acts

-0.14

POSITIVE LOGITS

 dealing

0.20

 governance

0.19

 expression

0.19

 approaching

0.19

 warfare

0.18

 measurement

0.18

 thinking

0.18

 communication

0.17

 Ð¼ÑĭÑĪ

0.16

 Governance

0.16

Activations Density 0.187%

phrases indicating methods or ways of working and their implications

No Comments

No Known Activations