INDEX

Explanations

references to nationalities or ethnic backgrounds in the context of individuals or brands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ahl

-0.16

ubs

-0.15

ÑĸÐ¶

-0.15

relude

-0.15

yses

-0.14

 Controls

-0.14

 addCriterion

-0.14

Manager

-0.14

tures

-0.13

;amp

-0.13

POSITIVE LOGITS

beh

0.16

 icon

0.16

 institution

0.15

edio

0.15

 giant

0.15

 wonder

0.14

ëıħ

0.14

abel

0.14

.sep

0.14

ENCHMARK

0.14

Activations Density 0.133%

references to nationalities or ethnic backgrounds in the context of individuals or brands

No Comments

No Known Activations