INDEX

Explanations

descriptors of positive qualities or attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ynchronously

-0.17

ÃŃ

-0.15

udd

-0.15

áº¹

-0.15

otal

-0.14

udi

-0.14

 moreover

-0.14

loh

-0.14

phan

-0.14

POSITIVE LOGITS

 intentions

0.21

intent

0.19

nes

0.19

 times

0.19

 Intent

0.19

 deeds

0.18

 intention

0.18

fortune

0.18

 guys

0.18

 Karma

0.17

Activations Density 0.061%

descriptors of positive qualities or attributes

No Comments

No Known Activations

descriptors of positive qualities or attributes

No Comments

No Known Activations