INDEX

Explanations

mentions of controversial topics or discussions surrounding moral or 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

malink

-0.18

elib

-0.16

Actually

-0.15

actually

-0.15

 Ð½Ð°Ð´Ð¾

-0.14

Asked

-0.14

too

-0.14

oka

-0.14

 Ð¿Ð¾ÑĤÐ¾Ð¼

-0.14

 Actually

-0.13

POSITIVE LOGITS

 According

0.23

 according

0.22

 Although

0.22

 While

0.21

 Though

0.21

According

0.21

Due

0.21

Furthermore

0.20

 although

0.20

due

0.20

Activations Density 0.264%

mentions of controversial topics or discussions surrounding moral or ethical dilemmas

No Comments

No Known Activations