INDEX

Explanations

technical references related to programming libraries and frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

æŃ©

-0.15

ocaust

-0.15

decess

-0.15

ERENCE

-0.15

zÃ¡

-0.14

ryn

-0.14

ŀ

-0.14

lyn

-0.14

arrants

-0.13

berger

-0.13

POSITIVE LOGITS

 latest

0.26

 version

0.25

latest

0.25

_VERSION

0.24

 Version

0.23

(version

0.23

version

0.23

 VERSION

0.23

 versions

0.22

_version

0.22

Activations Density 0.065%

technical references related to programming libraries and frameworks

No Comments

No Known Activations