INDEX

Explanations

information related to electronics and technology products, specifically focusing on brands, models, and their features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ihan

-0.16

irk

-0.15

 Vanilla

-0.14

illed

-0.14

 dipping

-0.14

entina

-0.14

 McKenzie

-0.13

ooter

-0.13

pper

-0.13

igan

-0.13

POSITIVE LOGITS

LG

0.25

HP

0.23

LG

0.21

HTC

0.20

 Philips

0.20

 Acer

0.19

 ASUS

0.19

Len

0.19

NEC

0.18

HT

0.18

Activations Density 0.105%

information related to electronics and technology products, specifically focusing on brands, models, and their features

No Comments

No Known Activations