INDEX

Explanations

references to personal preferences and experiences related to enjoyment and satisfaction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

hangi

-0.17

DataGridViewTextBoxColumn

-0.16

clave

-0.15

inent

-0.14

§

-0.14

toy

-0.14

ÑĥÐ»ÑıÑĢ

-0.14

WND

-0.14

otta

-0.13

MEDIA

-0.13

POSITIVE LOGITS

odore

0.16

 Truy

0.15

.GPIO

0.15

 Kens

0.14

orsch

0.14

etter

0.14

/Error

0.14

ica

0.13

bou

0.13

gesch

0.13

Activations Density 1.029%

references to personal preferences and experiences related to enjoyment and satisfaction

No Comments

No Known Activations