INDEX

Explanations

phrases indicating a sense of wrongdoing or moral issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

UTE

-0.17

croft

-0.16

ute

-0.16

Pur

-0.15

vit

-0.15

ervas

-0.14

xia

-0.14

ocaly

-0.14

ecom

-0.14

 otherwise

-0.14

POSITIVE LOGITS

achen

0.16

ollen

0.15

 Mean

0.15

inke

0.14

anner

0.14

ankind

0.14

elight

0.14

itler

0.14

favicon

0.14

åħ¶ä¸Ń

0.13

Activations Density 0.004%

phrases indicating a sense of wrongdoing or moral issues

No Comments

No Known Activations