INDEX

Explanations

elements related to moral and ethical dilemmas

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

Liter

-0.15

 Liter

-0.15

gaben

-0.14

untas

-0.14

anmar

-0.14

armor

-0.14

StateManager

-0.14

ITER

-0.14

ÙĪÙĩ

-0.14

-urlencoded

-0.13

POSITIVE LOGITS

 personally

0.20

0.17

 balance

0.17

Personally

0.16

 Personally

0.15

 Cave

0.15

 overall

0.15

ãģ¹ãģį

0.15

 Should

0.15

 personal

0.15

Activations Density 0.319%

elements related to moral and ethical dilemmas

No Comments

No Known Activations