INDEX

Explanations

references to precision and related terms

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

ÅĻ

-0.17

ysis

-0.16

herits

-0.15

acic

-0.15

.scalablytyped

-0.15

 Cooler

-0.15

flater

-0.15

FINITY

-0.15

 Cousins

-0.14

ochond

-0.14

POSITIVE LOGITS

prec

0.29

 prec

0.28

 Prec

0.28

Prec

0.27

ursors

0.22

ise

0.21

 precip

0.21

inct

0.20

ursor

0.20

 prÃ©c

0.20

Activations Density 0.011%

references to precision and related terms

No Comments

No Known Activations