INDEX

Explanations

terms related to ergonomics and ergonomic design

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ras

-0.17

ngine

-0.16

riangle

-0.16

LY

-0.15

ilib

-0.15

ikan

-0.15

ral

-0.15

lie

-0.15

ityEngine

-0.15

OperationException

-0.15

POSITIVE LOGITS

ues

0.21

.scalablytyped

0.18

0.17

ÑĥÐ¼ÐµÐ½ÑĤ

0.17

ued

0.16

ently

0.16

ards

0.16

hey

0.16

onaut

0.16

apers

0.15

Activations Density 0.040%

terms related to ergonomics and ergonomic design

No Comments

No Known Activations