INDEX

Explanations

terms related to mathematical concepts and properties, particularly in the context of spectra and dimensions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

coni

-0.16

 presence

-0.15

ì°°

-0.15

_presence

-0.14

.scalablytyped

-0.14

usercontent

-0.14

presence

-0.14

 certain

-0.13

znÃ¡m

-0.13

 spect

-0.13

POSITIVE LOGITS

ity

0.27

ness

0.24

ities

0.21

ITY

0.19

 counterpart

0.18

idad

0.18

 regime

0.17

NES

0.17

ilty

0.17

NESS

0.16

Activations Density 0.267%

terms related to mathematical concepts and properties, particularly in the context of spectra and dimensions

No Comments

No Known Activations