INDEX

Explanations

details about options, conditions, and additional charges in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ustil

-0.14

regn

-0.14

ingleton

-0.14

æľīäºº

-0.14

endforeach

-0.13

çŃĴ

-0.13

alom

-0.13

ÑģÑĤÐ¸Ð½

-0.13

.scalablytyped

-0.13

atform

-0.13

POSITIVE LOGITS

 extra

0.87

 additional

0.84

extra

0.67

additional

0.67

 Additional

0.65

 extras

0.64

 Extra

0.61

-extra

0.61

 EXTRA

0.61

Additional

0.60

Activations Density 0.709%

details about options, conditions, and additional charges in various contexts

No Comments

No Known Activations

details about options, conditions, and additional charges in various contexts

No Comments

No Known Activations