INDEX

Explanations

expressions related to moral judgments and ethical considerations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ucu

-0.17

ëĿ¼ìĿ´

-0.15

icip

-0.15

 audience

-0.14

ellung

-0.13

erv

-0.13

 Nico

-0.13

 Adapt

-0.13

ahas

-0.13

POSITIVE LOGITS

 Ð±Ð°Ð³

0.14

 getObject

0.14

crollView

0.14

 teng

0.14

tons

0.14

Ð»Ð¸Ð½Ð¸

0.14

vala

0.14

jejer

0.13

bug

0.13

abet

0.13

Activations Density 0.217%

expressions related to moral judgments and ethical considerations

No Comments

No Known Activations