INDEX

Explanations

terms and phrases related to unfairness and equity issues

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

heel

-0.16

.crm

-0.16

 completo

-0.15

ÙĩØ±Ùĩ

-0.15

iens

-0.14

><![

-0.14

ANDLE

-0.14

icit

-0.14

VERRIDE

-0.14

rgan

-0.14

POSITIVE LOGITS

erli

0.15

sla

0.14

etooth

0.14

 Gomez

0.14

lu

0.14

usercontent

0.13

avenport

0.13

gni

0.13

******/

0.13

anguard

0.13

Activations Density 0.001%

terms and phrases related to unfairness and equity issues

No Comments

No Known Activations