INDEX

Explanations

language learning tools and methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

sed

-0.17

åĬŁ

-0.15

å¿ł

-0.15

anta

-0.14

ground

-0.14

engo

-0.13

har

-0.13

 ìĦ¤

-0.13

Ð¿Ð¾ÑĢ

-0.13

çĭĹ

-0.13

POSITIVE LOGITS

elo

0.15

ElementType

0.15

FromArray

0.14

ISM

0.14

LEE

0.14

usting

0.13

Arena

0.13

ìĽĥ

0.13

/weather

0.13

 Residential

0.13

Activations Density 0.001%

language learning tools and methods

No Comments

No Known Activations