INDEX

Explanations

references to cosmetic or physical attributes and their perceived societal impacts

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

ÏģÏį

-0.16

ensburg

-0.15

Ð´Ð¾Ð²

-0.14

ÑĸÐ¼Ñĸ

-0.14

ilton

-0.14

digits

-0.13

rdf

-0.13

 independ

-0.13

ymoon

-0.13

\CMS

-0.13

POSITIVE LOGITS

 problem

0.24

.problem

0.23

problem

0.23

Wor

0.22

 Problem

0.22

 worry

0.22

åķıé¡Į

0.22

éĹ®é¢ĺ

0.21

 concern

0.20

 problema

0.20

Activations Density 0.266%

references to cosmetic or physical attributes and their perceived societal impacts

No Comments

No Known Activations