INDEX

Explanations

phrases that indicate ethical dilemmas or moral complexities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

umer

-0.17

 anymore

-0.16

 sometimes

-0.15

 Same

-0.15

amm

-0.14

 Sometimes

-0.14

?p

-0.14

æ§

-0.14

Nor

-0.14

sometimes

-0.14

POSITIVE LOGITS

hw

0.21

place

0.21

 sort

0.20

achine

0.18

-sort

0.18

 somewhere

0.18

 else

0.18

ones

0.17

 somew

0.17

ome

0.17

Activations Density 0.086%

phrases that indicate ethical dilemmas or moral complexities

No Comments

No Known Activations