INDEX

Explanations

elements and their relationships in various contexts, often focusing on structure and organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

PARATOR

-0.18

ury

-0.18

Yao

-0.15

ouser

-0.15

åłĤ

-0.14

apl

-0.14

iores

-0.13

ond

-0.13

istant

-0.13

POSITIVE LOGITS

ë§Īëĭ¤

0.19

 baÅŁÄ±na

0.17

isode

0.16

 individually

0.16

.PropTypes

0.15

.AutoComplete

0.15

asca

0.15

 separately

0.15

åıĬåħ¶

0.15

çĭ¬ç«ĭ

0.15

Activations Density 0.150%

elements and their relationships in various contexts, often focusing on structure and organization

No Comments

No Known Activations