INDEX

Explanations

phrases indicating possession or foundational aspects of subjects

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

alla

-0.18

è¾Ľ

-0.16

æĸ¹

-0.15

engo

-0.14

fits

-0.14

iner

-0.14

quisitions

-0.13

 Associ

-0.13

 fitting

-0.13

åĭĴ

-0.13

POSITIVE LOGITS

oloj

0.16

Î»Î¿Ïį

0.15

mÃ©na

0.15

RGBA

0.15

urgeon

0.15

oru

0.15

achi

0.14

.NewRequest

0.14

urat

0.14

Activations Density 0.038%

phrases indicating possession or foundational aspects of subjects

No Comments

No Known Activations