INDEX

Explanations

phrases related to technical compatibility and performance of devices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

clin

-0.17

allen

-0.16

.scalablytyped

-0.15

onica

-0.14

 corpor

-0.14

edes

-0.14

ussy

-0.14

lse

-0.14

 gettext

-0.14

avel

-0.14

POSITIVE LOGITS

 compatibility

0.19

 Telegram

0.16

ability

0.15

 Compatibility

0.15

 working

0.15

Compatibility

0.14

_working

0.14

tested

0.14

 native

0.13

BlockSize

0.13

Activations Density 0.044%

phrases related to technical compatibility and performance of devices

No Comments

No Known Activations