INDEX

Explanations

discussions centered around morality and its implications in society

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

oret

-0.17

 shall

-0.16

ley

-0.15

 thereby

-0.15

 thus

-0.15

leaf

-0.15

Cub

-0.15

fluid

-0.14

 main

-0.14

ilde

-0.14

POSITIVE LOGITS

jev

0.19

undler

0.17

.GPIO

0.16

eyen

0.15

kili

0.15

antity

0.14

ephir

0.14

omanip

0.14

á»Ļng

0.14

SEP

0.14

Activations Density 0.146%

discussions centered around morality and its implications in society

No Comments

No Known Activations