INDEX

Explanations

references to programming and mathematical concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

.scalablytyped

-0.17

 quant

-0.16

 Quant

-0.15

 quantify

-0.14

arel

-0.14

ÑĤÑĢÐ°

-0.14

Quant

-0.14

.Schema

-0.14

Kod

-0.14

 trailer

-0.14

POSITIVE LOGITS

scientific

0.25

TI

0.25

 scientific

0.24

TI

0.23

 Scientific

0.23

Scient

0.23

Pocket

0.23

 pocket

0.22

 ÐºÐ°Ð»ÑĮ

0.21

 Pocket

0.21

Activations Density 0.015%

references to programming and mathematical concepts

No Comments

No Known Activations

references to programming and mathematical concepts

No Comments

No Known Activations