INDEX

Explanations

terms related to inclusivity and diversity

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

addock

-0.16

arr

-0.16

arr

-0.15

erk

-0.14

 cann

-0.14

ondo

-0.14

stry

-0.14

Ð¸ÑģÐ»Ð¾Ð²

-0.14

 Harr

-0.14

Ã¡tor

-0.14

POSITIVE LOGITS

WISE

0.15

ê¹

0.15

coop

0.14

HandlerContext

0.14

etail

0.14

yon

0.14

olist

0.13

 Appe

0.13

afs

0.13

UNT

0.13

Activations Density 0.006%

terms related to inclusivity and diversity

No Comments

No Known Activations