INDEX

Explanations

statements reflecting personal opinions or subjective viewpoints

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ermann

-0.15

 horror

-0.14

 grav

-0.14

eneral

-0.14

owell

-0.14

 gone

-0.14

erman

-0.14

æ¿

-0.13

SSION

-0.13

MC

-0.13

POSITIVE LOGITS

 smart

0.27

SMART

0.25

smart

0.24

 wise

0.23

 Smart

0.23

 wisdom

0.22

 Wise

0.22

.smart

0.21

èģ

0.21

_smart

0.21

Activations Density 0.011%

statements reflecting personal opinions or subjective viewpoints

No Comments

No Known Activations