INDEX

Explanations

numerical data and metadata related to entries in a collection or database

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

peg

-0.16

igli

-0.15

enie

-0.15

-0.14

 affected

-0.14

-less

-0.14

ffect

-0.13

eld

-0.13

 indirect

-0.13

bcm

-0.13

POSITIVE LOGITS

deaux

0.16

porte

0.15

ARP

0.15

.PORT

0.14

<dd

0.13

fila

0.13

PORT

0.13

 Ð³Ð»Ð¸

0.13

.Guna

0.13

Qed

0.13

Activations Density 0.008%

numerical data and metadata related to entries in a collection or database

No Comments

No Known Activations