INDEX

Explanations

common names or terms associated with characteristics of zodiac signs and their related traits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

INGER

-0.16

.scalablytyped

-0.16

Î½Î¹Î±

-0.15

 Jahre

-0.15

ABSPATH

-0.14

 Kron

-0.14

 ÑħÑĢÐ°

-0.14

æ±Ĥè´Ń

-0.14

anden

-0.14

utenberg

-0.13

POSITIVE LOGITS

 Assassin

0.14

vais

0.14

 Redistributions

0.14

ãĥ³ãĥķ

0.13

ectors

0.13

à¤Ĥà¤¡

0.13

alia

0.13

quin

0.13

 sluts

0.13

 sophistication

0.13

Activations Density 0.046%

common names or terms associated with characteristics of zodiac signs and their related traits

No Comments

No Known Activations