INDEX

Explanations

technical terms and mathematical concepts related to signal processing and polarizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

eria

-0.21

 Convenience

-0.16

uler

-0.14

èĤ©

-0.14

itler

-0.14

ure

-0.14

eydi

-0.14

letcher

-0.13

oldt

-0.13

IDL

-0.13

POSITIVE LOGITS

baum

0.14

 Presence

0.14

Fin

0.14

fin

0.14

anners

0.13

pong

0.13

sten

0.13

leg

0.13

pte

0.13

Activations Density 0.179%

technical terms and mathematical concepts related to signal processing and polarizations

No Comments

No Known Activations