INDEX

Explanations

actions related to conflict and decisions involving moral dilemmas in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ovna

-0.15

enco

-0.14

/categories

-0.14

ancers

-0.14

 Withdraw

-0.14

Withdraw

-0.14

cede

-0.14

unj

-0.14

POSITIVE LOGITS

 kill

0.37

 kills

0.32

 killing

0.28

 killed

0.26

 dispatch

0.25

kill

0.25

 Kill

0.24

kills

0.23

 Killing

0.23

 Kills

0.23

Activations Density 0.334%

actions related to conflict and decisions involving moral dilemmas in narratives

No Comments

No Known Activations