INDEX

Explanations

references to pets and their significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

arkan

-0.15

 MÃľ

-0.14

illard

-0.14

chalk

-0.14

ovel

-0.14

 Babylon

-0.14

":["

-0.13

lotte

-0.13

roscope

-0.13

Ð¾ÑĢÐ¾Ð½

-0.13

POSITIVE LOGITS

fur

0.28

 humans

0.27

fur

0.27

pur

0.25

 Humans

0.25

 human

0.24

Humans

0.24

pur

0.23

Pur

0.22

paw

0.21

Activations Density 0.001%

references to pets and their significance

No Comments

No Known Activations