INDEX

Explanations

technical terms and questions related to programming, software, and user interaction

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

linger

-0.15

 Russo

-0.15

 Bylo

-0.15

 Cald

-0.14

BackingField

-0.14

OAD

-0.14

-Za

-0.14

-Mail

-0.14

.PIPE

-0.14

åĬĽçļĦ

-0.13

POSITIVE LOGITS

ergy

0.18

sen

0.16

 Lester

0.15

iere

0.15

 maneuver

0.14

own

0.14

aze

0.14

âĢİ

0.13

.mutable

0.13

AREA

0.13

Activations Density 0.002%

technical terms and questions related to programming, software, and user interaction

No Comments

No Known Activations